© 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. 108977
    Prev
    Next
    INDEX
    Explanations

    code/technical text

    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
     recieved
    -0.26
    è¿ĺæľīä»Ģä¹Ī
    -0.25
    è¿ĺæĺ¯
    -0.25
    è¿ĺæľīä¸Ģ个
    -0.25
    -League
    -0.25
    å±ŀæĢ§
    -0.25
    +-+-
    -0.24
    è¿ĺæľī
    -0.24
    _TypeInfo
    -0.24
    éĩijèŀįç§ijæĬĢ
    -0.24
    POSITIVE LOGITS
     Cot
    0.31
     co
    0.30
    isc
    0.28
     fl
    0.26
    illion
    0.25
    inic
    0.25
    compile
    0.25
    åıij
    0.25
    ç¥ĸåħĪ
    0.24
    key
    0.24
    Activations Density 0.103%

    No Known Activations