© 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. 15-RESID-POST-AA
    11. 4463
    Prev
    Next
    INDEX
    Explanations

    sodium

    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
    个别
    -0.08
    כול
    -0.07
     series
    -0.07
    _Custom
    -0.07
    Expand
    -0.07
    _item
    -0.07
     variable
    -0.07
    iew
    -0.07
    的最大
    -0.07
    包容
    -0.07
    POSITIVE LOGITS
    día
    0.07
    הליכ
    0.07
     Sodium
    0.07
    oncé
    0.07
     Cuando
    0.07
    意想不到
    0.07
    JSGlobal
    0.07
    odium
    0.07
     פני
    0.07
     sodium
    0.07
    Activations Density 0.009%

    No Known Activations