© 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. 141052
    Prev
    Next
    INDEX
    Explanations

    Extracts from varied sources

    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
    è°£
    -0.29
     sensed
    -0.29
    ä¸ĭ游
    -0.27
     &(
    -0.27
    ToAdd
    -0.26
     thereafter
    -0.26
    inia
    -0.26
    urther
    -0.25
    eree
    -0.25
     descendants
    -0.24
    POSITIVE LOGITS
    æī¶
    0.29
    æĬĢèĥ½åŁ¹è®Ń
    0.26
    ä¿IJ
    0.25
    :absolute
    0.24
    éĥijéĩį
    0.24
    çļĦä¸ĵä¸ļ
    0.24
    amax
    0.24
    isory
    0.24
    iest
    0.24
    ebp
    0.24
    Activations Density 6.093%

    No Known Activations