© 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. 149994
    Prev
    Next
    INDEX
    Explanations

    Greek letters

    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
     recurrent
    -0.25
    tures
    -0.24
    Dual
    -0.23
    æīįè¡Į
    -0.23
    ánd
    -0.23
     reciprocal
    -0.23
    æīįèĥ½
    -0.23
    ención
    -0.23
     twice
    -0.23
    acted
    -0.23
    POSITIVE LOGITS
    ÑĩÑĮ
    0.27
     Vince
    0.27
    ç»Ĵ
    0.26
    åķ¡
    0.26
    .sam
    0.24
     Tháng
    0.24
     ngủ
    0.24
    quine
    0.24
    .getHours
    0.23
    ä¸įå®Į
    0.23
    Activations Density 0.995%

    No Known Activations