© 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. 19-RESID-POST-AA
    11. 9003
    Prev
    Next
    INDEX
    Explanations

    accept

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-qwen2.5-7b-instruct/resid_post_layer_19/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.19.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     filing
    -0.07
    inan
    -0.07
     vz
    -0.07
    UGHT
    -0.07
    gado
    -0.07
    udas
    -0.06
    /dis
    -0.06
     hô
    -0.06
     bz
    -0.06
     gdk
    -0.06
    POSITIVE LOGITS
     accepted
    0.08
     percent
    0.07
     merchant
    0.07
    셢
    0.07
     converters
    0.07
     процент
    0.07
    مست
    0.06
    江
    0.06
     مست
    0.06
    .Mark
    0.06
    Activations Density 0.023%

    No Known Activations