© 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. 24706
    Prev
    Next
    INDEX
    Explanations

    Rules and regulations

    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
    .advance
    -0.28
    advance
    -0.27
    jen
    -0.24
    covery
    -0.24
    èħĶ
    -0.23
    å¨
    -0.23
     üzerine
    -0.23
    _UNUSED
    -0.23
    ism
    -0.23
    logy
    -0.23
    POSITIVE LOGITS
    äºĨ个
    0.32
    alus
    0.32
    åIJ¬åIJ¬
    0.27
    edBy
    0.26
    æľ¬æĬ¥
    0.26
    æĪªèĩ³
    0.25
     slightly
    0.25
    bate
    0.25
    äºĨäºĽ
    0.25
    -che
    0.25
    Activations Density 0.009%

    No Known Activations