© 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. 23-TRANSCODER-HP
    7. 23931
    Prev
    Next
    INDEX
    Explanations

    Code snippets, use "instead"

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_23.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.23.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    hausen
    -0.28
    å°ļæľª
    -0.26
    atter
    -0.26
    lob
    -0.25
    shed
    -0.24
    è¿ĺæľª
    -0.24
    ãĤ·ãĥ£
    -0.24
    è¿ĺ没æľī
    -0.24
    Ùģار
    -0.23
    etail
    -0.23
    POSITIVE LOGITS
     instead
    1.43
    instead
    1.28
     Instead
    1.19
    Instead
    1.18
     вмеÑģÑĤ
    0.99
    ä»£æĽ¿
    0.96
    èĢĮæĺ¯
    0.90
    æĽ¿ä»£
    0.80
     inve
    0.72
    åıįèĢĮ
    0.72
    Activations Density 0.003%

    No Known Activations