© 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. 57083
    Prev
    Next
    INDEX
    Explanations

    options

    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
     encountered
    -0.32
    .sz
    -0.28
    è¨Ģ
    -0.28
     approached
    -0.27
    è¾Ħ
    -0.26
     Gu
    -0.26
     neck
    -0.26
     tended
    -0.25
    Gu
    -0.25
    两ä¸ī
    -0.25
    POSITIVE LOGITS
    åı¯çĶ¨
    0.39
    oppable
    0.32
    -Based
    0.31
     available
    0.30
     availability
    0.29
    AVAILABLE
    0.29
    çĶ¨äºº
    0.29
    _available
    0.28
     Available
    0.28
    Available
    0.27
    Activations Density 0.003%

    No Known Activations