© 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. 14-TRANSCODER-HP
    7. 40500
    Prev
    Next
    INDEX
    Explanations

    as

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_14.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.14.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Framework
    -0.33
    ä»ĸæĺ¯
    -0.29
    _framework
    -0.29
    éĹ³
    -0.28
     framework
    -0.28
    åıĸ代
    -0.28
    æĭ¼éŁ³
    -0.28
     frameworks
    -0.28
    çĪ·
    -0.26
    Activ
    -0.26
    POSITIVE LOGITS
     Morg
    0.27
     rever
    0.26
    pers
    0.25
     Gould
    0.25
    lated
    0.25
    .lesson
    0.25
    èݪ
    0.24
    say
    0.24
     conversion
    0.24
    ected
    0.23
    Activations Density 0.223%

    No Known Activations