© 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. Qwen3-4B
    5. 25-TRANSCODER-HP
    7. 108186
    Prev
    Next
    INDEX
    Explanations

    Education and degrees

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_25.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.25.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     continua
    -0.26
     Employment
    -0.26
    åŁł
    -0.25
    entr
    -0.25
    recognized
    -0.24
    åįģäºĶ
    -0.24
    æĸ¹å¼ıè¿Ľè¡Į
    -0.24
    ento
    -0.24
    lington
    -0.24
    ctest
    -0.24
    POSITIVE LOGITS
    æŀģ
    0.27
    body
    0.26
    éĻĤ
    0.26
    ç®ħ
    0.26
    @class
    0.26
    ä¸ĭ鼨
    0.26
    åºĶä»ĺ
    0.25
    çĶ¨éĩı
    0.25
    inally
    0.25
    .getBody
    0.24
    Activations Density 0.923%

    No Known Activations