© 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. 15-RESID-POST-AA
    11. 121841
    Prev
    Next
    INDEX
    Explanations

    computer code and logs

    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_15/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     זכא
    -0.07
    DRV
    -0.07
    .labelX
    -0.07
                
↵
    -0.06
    띳
    -0.06
     **/↵
    -0.06
    |m
    -0.06
     tsl
    -0.06
    ��
    -0.06
     Shemale
    -0.06
    POSITIVE LOGITS
    接纳
    0.07
    رك
    0.07
    钣
    0.07
    .central
    0.07
     silly
    0.07
     Ris
    0.07
     реак
    0.07
     collaborative
    0.07
    ег
    0.07
    Spirit
    0.07
    Activations Density 0.043%

    No Known Activations