© 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. 150777
    Prev
    Next
    INDEX
    Explanations

    computer code/technical documents

    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
    urai
    -0.30
     SAC
    -0.27
    å¿ħè¦ģ
    -0.26
    nge
    -0.26
    ddf
    -0.25
    æīĵè´¥
    -0.25
    ctor
    -0.25
    itor
    -0.25
    ä¹Łå°Ĩ
    -0.24
    pper
    -0.24
    POSITIVE LOGITS
    æŁIJç§į
    0.33
     tÆ°á»Łng
    0.31
    æľīä¸Ģç§į
    0.29
    vo
    0.29
    åı¦ä¸Ģç§į
    0.28
    ä¸Ģç§į
    0.27
    æľīæŶ
    0.26
    ãĤ¯ãĥŃ
    0.25
    voices
    0.25
     sometimes
    0.25
    Activations Density 3.018%

    No Known Activations