© 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. 64453
    Prev
    Next
    INDEX
    Explanations

    working

    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
    sj
    -0.29
    sx
    -0.28
    sen
    -0.26
    su
    -0.26
    ider
    -0.26
    sa
    -0.25
    en
    -0.24
    san
    -0.24
     Sweat
    -0.24
    aso
    -0.24
    POSITIVE LOGITS
    åıijå±ķæĸ¹åIJij
    0.28
    å¹ħ
    0.26
    getitem
    0.26
    .realm
    0.26
    æĹ¥çĶµ
    0.25
    产ä¸ļåįĩ级
    0.25
    atter
    0.24
    åıijå±ķ空éĹ´
    0.24
    ielding
    0.24
    heap
    0.23
    Activations Density 30.121%

    No Known Activations