© 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. 40285
    Prev
    Next
    INDEX
    Explanations

    Random/Uncommon characters in text

    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
    ç»Ī身
    -0.29
     dip
    -0.27
     sil
    -0.26
     dipping
    -0.26
    setFlash
    -0.25
    å¥Ĺ
    -0.25
    æī£
    -0.24
    jeta
    -0.24
     dips
    -0.24
    ä½ľä¸ºä¸Ģ个
    -0.24
    POSITIVE LOGITS
     key
    0.27
    azzi
    0.25
    olic
    0.25
    ansi
    0.24
    (Key
    0.24
    ouncer
    0.24
    åĪĩåħ¥
    0.24
    áĥ©
    0.24
     Câm
    0.23
    estroy
    0.23
    Activations Density 0.092%

    No Known Activations