© 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. 8227
    Prev
    Next
    INDEX
    Explanations

    Code and names with "Von"

    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
     result
    -0.66
    ç»ĵæŀľ
    -0.61
    result
    -0.57
    çļĦç»ĵæŀľ
    -0.54
    (result
    -0.54
    .result
    -0.53
     resulting
    -0.53
     resultado
    -0.49
    çµIJæŀľ
    -0.49
    Result
    -0.47
    POSITIVE LOGITS
    ToJson
    0.27
    æĦŁåħ´è¶£çļĦ
    0.25
    .AppSettings
    0.25
    ç«ĭä½ĵ
    0.25
    éĽĦåİļ
    0.24
     BaseService
    0.24
    eyJ
    0.24
    ä¾Ķ
    0.24
    转移åĪ°
    0.24
    -pe
    0.23
    Activations Density 0.009%

    No Known Activations