© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    5. Qwen2.5-7B-IT
    7. Resid Post - 131k
    9. 7-RESID-POST-AA
    11. 58034
    Prev
    Next
    INDEX
    Explanations

    Notion API or Quora

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-qwen2.5-7b-instruct/resid_post_layer_7/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.7.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    jähr
    -0.07
    _jButton
    -0.07
    volução
    -0.07
     cope
    -0.07
    ющих
    -0.06
     béné
    -0.06
    部分
    -0.06
    -sign
    -0.06
     Cri
    -0.06
     службы
    -0.06
    POSITIVE LOGITS
    Ip
    0.07
     Scotch
    0.07
     Accident
    0.07
     Hilton
    0.07
    ↵            
↵
    0.07
    phem
    0.07
     insane
    0.07
     kad
    0.07
    ık
    0.07
                                            ↵
    0.07
    Activations Density 0.001%

    No Known Activations