© 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. 15-RESID-POST-AA
    6. 52287
    Prev
    Next
    INDEX
    Explanations

    under

    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
    盟
    -0.07
     MMO
    -0.07
    군
    -0.07
     Quentin
    -0.07
    ugal
    -0.07
     WTF
    -0.07
    etwork
    -0.06
    阵
    -0.06
     Staff
    -0.06
    nce
    -0.06
    POSITIVE LOGITS
    引来
    0.08
    (__('
    0.08
     своими
    0.08
    תחת
    0.07
    =\""
    0.07
    Interval
    0.07
     Typography
    0.07
     typography
    0.07
    مشاركات
    0.07
     *)__
    0.07
    Activations Density 0.003%

    No Known Activations