© 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. 107571
    Prev
    Next
    INDEX
    Explanations

    technical language

    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
    èµ·
    -0.28
    Push
    -0.28
    ademic
    -0.27
    ırım
    -0.26
    æıIJåĩº
    -0.26
    ajar
    -0.26
    寸
    -0.26
    设计æĸ¹æ¡Ī
    -0.25
    宣å¸ĥ
    -0.25
    åıijè¨Ģ人
    -0.25
    POSITIVE LOGITS
    ackers
    0.26
     offsetof
    0.26
    íļį
    0.25
    idia
    0.25
    .Null
    0.25
    IllegalArgumentException
    0.24
    OrderId
    0.24
    ivement
    0.24
     Intermediate
    0.24
    è¹Ĵ
    0.24
    Activations Density 0.901%

    No Known Activations