© 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. 150839
    Prev
    Next
    INDEX
    Explanations

    source code

    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
    èĮ¸
    -0.29
     Bened
    -0.29
    è¿Ļ家åħ¬åı¸
    -0.27
    èĨĺ
    -0.26
    å¹³åı°ä¸Ĭ
    -0.26
    楮
    -0.25
    пÑĭ
    -0.25
    建档ç«ĭåį¡
    -0.24
    unts
    -0.24
     mill
    -0.24
    POSITIVE LOGITS
     unknow
    0.25
    akan
    0.25
     waterfall
    0.23
     Europa
    0.23
    igt
    0.23
     actually
    0.23
     dungeon
    0.23
     categoryName
    0.23
     habit
    0.23
    ä¸Ģä½ĵ
    0.23
    Activations Density 0.037%

    No Known Activations