© 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. 31-TRANSCODER-HP
    7. 18326
    Prev
    Next
    INDEX
    Explanations

    Neg

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_31.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.31.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ä»İä¸ļ
    -0.25
    zl
    -0.25
    zure
    -0.25
     Cord
    -0.24
    ä¸ĭ车
    -0.24
    cba
    -0.24
    渤
    -0.24
     Thought
    -0.24
    itemId
    -0.24
    XC
    -0.23
    POSITIVE LOGITS
    ä¸į符åIJĪ
    0.30
    bsp
    0.29
    terminal
    0.28
     exactly
    0.27
     grate
    0.26
    iph
    0.26
    æĹĹ
    0.26
     feeling
    0.26
    æ´Ĺæīĭ
    0.25
    æķ£
    0.25
    Activations Density 1.187%

    No Known Activations