© 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. 41068
    Prev
    Next
    INDEX
    Explanations

    Computer related texts

    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
    ä¸ī家
    -0.32
    åĩłå®¶
    -0.29
    çŁ¢
    -0.27
    Editable
    -0.25
    ippi
    -0.25
    ileo
    -0.25
    äºİæĺ¯
    -0.25
     therap
    -0.24
    ani
    -0.24
    äge
    -0.24
    POSITIVE LOGITS
     Hu
    0.27
     Humb
    0.25
    HU
    0.25
    hu
    0.24
    çĥŃ度
    0.24
     ké
    0.24
    æįIJ
    0.24
    _COMMIT
    0.23
    ondon
    0.23
    indows
    0.23
    Activations Density 0.801%

    No Known Activations