© 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. 109496
    Prev
    Next
    INDEX
    Explanations

    /en

    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
    这一点
    -0.07
    Command
    -0.07
     admits
    -0.07
    .Task
    -0.07
    udu
    -0.06
    难道
    -0.06
    噻
    -0.06
     Battles
    -0.06
    igraphy
    -0.06
     salvar
    -0.06
    POSITIVE LOGITS
     cat
    0.08
     wxT
    0.07
    (et
    0.07
     repaint
    0.07
    consistent
    0.07
    August
    0.07
    _verified
    0.07
     PT
    0.06
    보호
    0.06
    可以在
    0.06
    Activations Density 0.001%

    No Known Activations