© 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. 141378
    Prev
    Next
    INDEX
    Explanations

    code and technical documentation

    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
    æ¸IJ
    -0.26
    çªģåĽ´
    -0.26
    nite
    -0.26
    éĹ®é¢ĺæĺ¯
    -0.25
    è´¨éĩıéĹ®é¢ĺ
    -0.25
     shameful
    -0.24
    èĩĤ
    -0.24
    atical
    -0.24
    ä¸ŃéĢĶ
    -0.24
    主é¢ĺ
    -0.23
    POSITIVE LOGITS
     unchanged
    0.35
    æĹłéľĢ
    0.31
    noop
    0.30
    ä¸įåģļ
    0.28
    ä¸įéľĢè¦ģ
    0.28
    没æľīä»»ä½ķ
    0.28
     plain
    0.28
    å®Įåħ¨æ²¡æľī
    0.27
     unrelated
    0.27
    æĹłæīĢè°ĵ
    0.27
    Activations Density 47.364%

    No Known Activations