© 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. 15-RESID-POST-AA
    11. 25730
    Prev
    Next
    INDEX
    Explanations

    Attempting a method

    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
     blat
    -0.07
    zas
    -0.07
    _VOLUME
    -0.07
    以其
    -0.07
    afd
    -0.07
     protesting
    -0.07
    .Black
    -0.07
    {id
    -0.07
     fleets
    -0.06
    oble
    -0.06
    POSITIVE LOGITS
     listItem
    0.07
     lij
    0.07
     החיים
    0.07
    .isArray
    0.07
     anyways
    0.07
    iatrics
    0.07
     Esc
    0.06
     camb
    0.06
     sigu
    0.06
    [keys
    0.06
    Activations Density 0.155%

    No Known Activations