© 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. 63462
    Prev
    Next
    INDEX
    Explanations

    Technical descriptions and usage

    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
    éĥ½æ²¡
    -0.30
    éĥ½ä¸įæķ¢
    -0.30
     ли
    -0.28
    ä¸įæķ¢
    -0.27
    åį´æĺ¯
    -0.27
    ç§ĭ
    -0.26
    åħĭ
    -0.26
    éĥ½æĹłæ³ķ
    -0.25
    uridad
    -0.25
    abay
    -0.25
    POSITIVE LOGITS
    agate
    0.29
    punkt
    0.25
    ген
    0.24
    __).
    0.24
    rias
    0.24
     executing
    0.24
     ayr
    0.23
    ä¹Łå°Ĩ
    0.23
    çű
    0.23
    åĩºçīĪ社
    0.23
    Activations Density 24.295%

    No Known Activations