© 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
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Qwen2.5-7B-IT
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 42201
    Prev
    Next
    INDEX
    Explanations

    book excerpts

    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_11/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     probably
    -0.08
    ipl
    -0.07
    _js
    -0.07
    эм
    -0.07
    锳
    -0.07
    enn
    -0.06
    饮用水
    -0.06
    MG
    -0.06
     eclectic
    -0.06
    ank
    -0.06
    POSITIVE LOGITS
    ਆ
    0.08
    POCH
    0.08
     graf
    0.08
    ظام
    0.07
    .sal
    0.07
     gratuit
    0.07
     sched
    0.07
    filt
    0.07
     Qty
    0.07
    熹
    0.07
    Activations Density 0.080%

    No Known Activations