© 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. 31-TRANSCODER-HP
    7. 18213
    Prev
    Next
    INDEX
    Explanations

    Non-English tokens

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_31.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.31.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    æĥħ人
    -0.33
    åĩºç§Ł
    -0.25
    ç½Ķ
    -0.25
    zan
    -0.25
    leta
    -0.24
    åĪĨ辨
    -0.24
    crud
    -0.24
    fluence
    -0.24
    èĩªç§ģ
    -0.24
    ashington
    -0.24
    POSITIVE LOGITS
    ç½ijå°ıç¼ĸ
    0.31
    訴
    0.28
    è¯ī
    0.26
    çĶŁæĢģç³»ç»Ł
    0.25
     pursued
    0.25
    追
    0.25
    æľ¬ç«Ļ
    0.24
    tx
    0.23
     substit
    0.23
    è¡Ķ
    0.23
    Activations Density 1.617%

    No Known Activations