© 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 EvalsExportsinterp-engineNEWAPI 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. 81656
    Prev
    Next
    INDEX
    Explanations

    opportunity

    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
     disables
    -0.08
    怯
    -0.07
     Pavel
    -0.07
    FormGroup
    -0.07
    amel
    -0.07
    igel
    -0.07
     gave
    -0.07
    iclass
    -0.07
     cabe
    -0.07
    أل
    -0.07
    POSITIVE LOGITS
    סכום
    0.07
    دائرة
    0.07
    xAD
    0.07
    зам
    0.07
     trochę
    0.07
    РА
    0.06
    .Predicate
    0.06
    昆山
    0.06
    _numbers
    0.06
    如下
    0.06
    Activations Density 0.005%

    No Known Activations