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

    Neuronpedia

    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. 23-RESID-POST-AA
    11. 129620
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-qwen2.5-7b-instruct/resid_post_layer_23/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.23.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     ProductService
    -0.08
     deals
    -0.07
     dub
    -0.07
     Cele
    -0.07
     시
    -0.07
     coordin
    -0.07
    Dub
    -0.07
    _Close
    -0.07
     Teach
    -0.07
    TB
    -0.07
    POSITIVE LOGITS
    -vector
    0.07
    erais
    0.07
    renom
    0.07
     Petra
    0.07
    性感
    0.07
     alignSelf
    0.07
    EDA
    0.06
    .array
    0.06
    _persona
    0.06
    让自己
    0.06
    Activations Density 0.122%

    No Known Activations