© 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. 8426
    Prev
    Next
    INDEX
    Explanations

    Code and foreign languages

    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
    ramento
    -0.27
    说æľį
    -0.25
    æĿ¥çĶµ
    -0.25
    poi
    -0.24
    çĵ¢
    -0.23
    å®ĮåĸĦ
    -0.23
    NC
    -0.23
     SEN
    -0.23
     Stat
    -0.23
    imon
    -0.23
    POSITIVE LOGITS
    AttributeValue
    0.28
    idity
    0.27
    ald
    0.27
    åĵģå¾·
    0.25
    çķĮ
    0.24
     INLINE
    0.24
     unst
    0.24
    feed
    0.24
    (feed
    0.24
    ading
    0.24
    Activations Density 0.000%

    No Known Activations