© 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. 40405
    Prev
    Next
    INDEX
    Explanations

    reported

    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
    agento
    -0.31
    alon
    -0.29
    wordpress
    -0.27
    åĦ¿ç§ij
    -0.26
     WON
    -0.26
    OfWork
    -0.25
    _Work
    -0.25
    ä¸ªå·¥ä½ľ
    -0.25
    Verb
    -0.25
    oho
    -0.25
    POSITIVE LOGITS
    -important
    0.30
     commitments
    0.26
    Bush
    0.25
    è¯ī
    0.25
    çªĦ
    0.24
    åįģåĪĨéĩįè¦ģ
    0.24
    ä¸ĩä¸Ģ
    0.24
    --,
    0.23
    ocha
    0.23
    ä¸Ģçľĭ
    0.23
    Activations Density 3.212%

    No Known Activations