© 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. 11-RESID-POST-AA
    11. 109490
    Prev
    Next
    INDEX
    Explanations

    "//"

    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_11/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Isl
    -0.07
    isd
    -0.07
    -contrib
    -0.06
    Addresses
    -0.06
    状态
    -0.06
     Included
    -0.06
    职
    -0.06
     Background
    -0.06
     screened
    -0.06
     Assess
    -0.06
    POSITIVE LOGITS
    EndElement
    0.07
    _STMT
    0.07
    ✯
    0.07
    货运
    0.07
     człowiek
    0.07
     relay
    0.07
    Concat
    0.07
     reim
    0.06
    /string
    0.06
    _PHY
    0.06
    Activations Density 0.014%

    No Known Activations