© 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. 150102
    Prev
    Next
    INDEX
    Explanations

    Technical/scientific texts

    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
    ording
    -0.27
    URNS
    -0.26
    æĢİ
    -0.25
    atern
    -0.24
    å¤ı天
    -0.24
    åĵªåĦ¿
    -0.24
    .spec
    -0.24
    ãĤĤãĤī
    -0.24
    /Foundation
    -0.24
    notice
    -0.24
    POSITIVE LOGITS
     meanwhile
    0.32
    ä¸İæѤåIJĮæŶ
    0.29
     moreover
    0.28
    讫
    0.27
    ä¸įä»ħå¦ĤæѤ
    0.27
    é¡·
    0.27
     However
    0.26
    çĻ»åľº
    0.26
    itus
    0.25
    缸è¯Ĩ
    0.25
    Activations Density 1.618%

    No Known Activations