© 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. 64370
    Prev
    Next
    INDEX
    Explanations

    choices, options, processes

    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
    åŁºæľ¬
    -0.32
    ä¸İåħ¶
    -0.28
    ä¸İåħ¶ä»ĸ
    -0.28
     Vs
    -0.27
    fund
    -0.26
    ând
    -0.25
     vs
    -0.25
    åģľ
    -0.25
    Ä±ÅŁ
    -0.25
     prefixes
    -0.25
    POSITIVE LOGITS
    åįĹè·¯
    0.32
    æĪijå¸ĮæľĽ
    0.30
    åĮĹè·¯
    0.29
    åħīéĺ´
    0.26
    ä¹ŁåĽłæѤ
    0.26
    ä¸įæĸ¹ä¾¿
    0.26
    .design
    0.25
     Broadcom
    0.25
     Baghd
    0.25
     reason
    0.24
    Activations Density 14.245%

    No Known Activations