© 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. 27-TRANSCODER-HP
    7. 58098
    Prev
    Next
    INDEX
    Explanations

    identification

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_27.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.27.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    rew
    -0.29
    isters
    -0.28
    é¢Ĺ
    -0.27
    arer
    -0.27
    resh
    -0.26
    ç»ĵç®Ĺ
    -0.25
    uger
    -0.25
     Lis
    -0.24
    ores
    -0.24
    缴è¾ĸ
    -0.24
    POSITIVE LOGITS
    åIJł
    0.28
    è§Ħç¨ĭ
    0.27
    pth
    0.27
     awaits
    0.27
    Ready
    0.25
    åįıå®ļ
    0.25
    worthy
    0.25
    æijŀ
    0.25
    èģĶæĥ³
    0.25
     wor
    0.25
    Activations Density 0.065%

    No Known Activations