© 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. 20-TRANSCODER-HP
    7. 64035
    Prev
    Next
    INDEX
    Explanations

    science fiction and fantasy

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_20.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.20.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    çĶŁæ´»
    -0.26
    ä½ľä¸ļ
    -0.25
    ORS
    -0.25
    å½ĴæĿ¥
    -0.24
    izacion
    -0.24
     supper
    -0.24
    istributed
    -0.23
    _lv
    -0.23
    ç«
    -0.23
    综åIJĪ
    -0.23
    POSITIVE LOGITS
    adt
    0.31
    itin
    0.28
     Kingston
    0.26
    ä¸Ĭ游
    0.26
     seamless
    0.25
    çĥ
    0.25
    ä¸Ĭä¸ĭ游
    0.25
    :url
    0.25
    MAKE
    0.25
    ={['
    0.24
    Activations Density 4.511%

    No Known Activations