© 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. 19-TRANSCODER-HP
    7. 8908
    Prev
    Next
    INDEX
    Explanations

    Code and boolean logic

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_19.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.19.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     fails
    -0.32
    è¾¾ä¸įåĪ°
    -0.31
    åıªèĥ½
    -0.30
    åĭī强
    -0.30
    è¦ģæĥ³
    -0.30
    åıªå¥½
    -0.29
     unsuccessful
    -0.29
    è¯ļå®ŀ
    -0.28
    éĥ½æĹłæ³ķ
    -0.28
     attempted
    -0.28
    POSITIVE LOGITS
    ä¸įéľĢè¦ģ
    0.37
    æĹłéľĢ
    0.34
    ä¸įçĶ¨
    0.31
    ä¸įå¿ħ
    0.30
    åıªéľĢè¦ģ
    0.29
    itet
    0.29
    åħ¬æĬ¥
    0.29
    ä¸įéĻIJ
    0.28
    ewear
    0.27
    åıªéľĢ
    0.26
    Activations Density 0.719%

    No Known Activations