© 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. 14-TRANSCODER-HP
    7. 40917
    Prev
    Next
    INDEX
    Explanations

    time duration

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_14.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.14.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     fun
    -0.29
    Di
    -0.26
     di
    -0.26
    éŁ³
    -0.25
     ton
    -0.25
    LIN
    -0.25
     verb
    -0.24
     feedback
    -0.24
    ardon
    -0.24
     ob
    -0.24
    POSITIVE LOGITS
    ä¸¤åĽ½
    0.25
     Knox
    0.24
    pute
    0.24
    èIJ¥åķĨ
    0.24
    LOCATION
    0.24
     Bannon
    0.23
    顺åĪ©å®ĮæĪIJ
    0.23
     itemList
    0.23
     LOCATION
    0.23
    éĿŀ常é«ĺ
    0.23
    Activations Density 0.019%

    No Known Activations