© 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. 63871
    Prev
    Next
    INDEX
    Explanations

    directions

    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
    ifr
    -0.31
    æĻ¯çĤ¹
    -0.28
    åIJį为
    -0.28
    lien
    -0.26
    管çIJĨå·¥ä½ľ
    -0.25
    åIJį人
    -0.25
    еÑĩен
    -0.24
    åĪĨéĴŁåIJİ
    -0.24
     Tiá»ģn
    -0.24
    éĩijå±±
    -0.24
    POSITIVE LOGITS
     Paste
    0.27
    -i
    0.27
    in
    0.26
    éĢĨ
    0.26
     merch
    0.26
    èĪĨ
    0.26
    /types
    0.25
    i
    0.25
    ong
    0.25
    er
    0.25
    Activations Density 1.834%

    No Known Activations