© 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. 23-RESID-POST-AA
    6. 129797
    Prev
    Next
    INDEX
    Explanations

    is

    np_max-act-logits · gemini-2.0-flashTriggered by @bettyfeng2003
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-qwen2.5-7b-instruct/resid_post_layer_23/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.23.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Seeing
    -0.08
    묵
    -0.08
    菼
    -0.07
    そうだ
    -0.07
    改成
    -0.07
    OfSize
    -0.07
    OrUpdate
    -0.07
     Clubs
    -0.07
    ㊟
    -0.07
    MenuItem
    -0.07
    POSITIVE LOGITS
     is
    0.14
     are
    0.08
    时
    0.07
    /is
    0.07
    ㎰
    0.07
    ﲞ
    0.07
    -confidence
    0.07
     conspir
    0.07
     Kron
    0.07
     werde
    0.07
    Activations Density 1.404%

    No Known Activations