© 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. 56790
    Prev
    Next
    INDEX
    Explanations

    technical issues

    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
    æĹłæķĪ
    -0.73
     ineffective
    -0.57
     inappropriate
    -0.56
     invalid
    -0.56
     incorrect
    -0.52
    ä¸įåIJĪéĢĤ
    -0.49
    invalid
    -0.49
    ä¸įèī¯
    -0.49
     wrong
    -0.48
     inefficient
    -0.48
    POSITIVE LOGITS
    Attachments
    0.26
    planes
    0.26
    OptionsMenu
    0.24
    plane
    0.24
    apped
    0.24
     interrupts
    0.23
    ä¸įåĨį
    0.23
    åĢŁçĶ¨
    0.23
    interrupt
    0.23
    itant
    0.23
    Activations Density 0.003%

    No Known Activations