© 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. 9303
    Prev
    Next
    INDEX
    Explanations

    say bleeding

    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
    phil
    -0.27
    tü
    -0.27
    çŃ·åŃIJ
    -0.27
    (EC
    -0.26
    ycop
    -0.26
    äºĭä¸ļåıijå±ķ
    -0.25
    fried
    -0.25
     Lud
    -0.24
    Cancelled
    -0.24
    arged
    -0.24
    POSITIVE LOGITS
    åĩºè¡Ģ
    0.44
    æ³Ħæ¼ı
    0.40
     bleeding
    0.38
    æ¼ı
    0.36
    æ³Ħéľ²
    0.34
     leak
    0.33
    æµģåĩº
    0.31
     Ble
    0.29
    hem
    0.29
     bleed
    0.29
    Activations Density 0.000%

    No Known Activations