© 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. 24574
    Prev
    Next
    INDEX
    Explanations

    Function words

    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
    è¿Ļæĺ¯
    -0.27
    åĽ¾ä¸º
    -0.26
    ãĤĬ
    -0.25
    'č↵č↵
    -0.25
    ä¼ļæľī
    -0.24
    ']].
    -0.24
    è¥Ħ
    -0.24
    /~
    -0.24
    è¿ĺæľī
    -0.24
     reminds
    -0.24
    POSITIVE LOGITS
     unless
    0.37
     despite
    0.36
     except
    0.33
    尽管
    0.33
     aside
    0.32
     contrary
    0.31
    unless
    0.31
     apart
    0.30
    èĻ½çĦ¶
    0.29
     Apart
    0.29
    Activations Density 0.005%

    No Known Activations