© 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. 24-TRANSCODER-HP
    7. 150748
    Prev
    Next
    INDEX
    Explanations

    Edward

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_24.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.24.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ä»įæĺ¯
    -0.28
    ä»Ģä¹Īåij¢
    -0.25
    _needed
    -0.25
    chief
    -0.25
     detriment
    -0.25
     bona
    -0.24
     trông
    -0.24
     usefulness
    -0.24
    çİ©æ³ķ
    -0.23
    ä¸įåħį
    -0.23
    POSITIVE LOGITS
     Glob
    0.26
     invest
    0.24
     globe
    0.24
     Fi
    0.24
     glob
    0.24
    .glob
    0.24
    phant
    0.23
     subt
    0.23
    ald
    0.23
     ald
    0.23
    Activations Density 1.637%

    No Known Activations