© 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. 35360
    Prev
    Next
    INDEX
    Explanations

    resource

    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
    فة
    -0.06
    的表情
    -0.06
     quoi
    -0.06
    sdk
    -0.06
    Animation
    -0.06
    ﺧ
    -0.06
    .addComponent
    -0.06
    ú
    -0.06
    ო
    -0.06
     refreshing
    -0.06
    POSITIVE LOGITS
     Mechan
    0.07
     технолог
    0.07
    你的
    0.07
    نشأ
    0.07
     Tes
    0.07
     tabel
    0.07
    estring
    0.07
    亲戚
    0.07
    .Import
    0.07
    แดน
    0.07
    Activations Density 0.002%

    No Known Activations