© 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. 57047
    Prev
    Next
    INDEX
    Explanations

    Foreign words

    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
    æĶ¯æĮģ
    -0.31
    åįıåĬ©
    -0.29
     support
    -0.28
     assistance
    -0.28
     help
    -0.27
    Hor
    -0.26
    帮åĬ©
    -0.26
    çļĦæĶ¯æĮģ
    -0.26
     aid
    -0.25
     bada
    -0.25
    POSITIVE LOGITS
    ä½ľèĢħæīĢæľī
    0.29
    eral
    0.28
    anders
    0.27
    åĪ¶åº¦æĶ¹éĿ©
    0.27
    à¹ģà¸ŀà¸Ĺย
    0.26
    ındaki
    0.25
    çľģéĴ±
    0.25
    ByVersion
    0.25
    continental
    0.24
    æ³ķå¾ĭæ³ķè§Ħ
    0.24
    Activations Density 0.000%

    No Known Activations