© 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. 58244
    Prev
    Next
    INDEX
    Explanations

    commercial

    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
    åŁºæķ°
    -0.28
    ä¿¡æģ¯åħ¬å¼Ģ
    -0.28
     Proto
    -0.27
    fad
    -0.27
    踪
    -0.26
    çķĻä¸ĭäºĨ
    -0.26
     basis
    -0.26
    pread
    -0.25
     sede
    -0.25
    éĿŀçī©è´¨
    -0.25
    POSITIVE LOGITS
     commercially
    0.31
     Commercial
    0.27
     commercial
    0.27
     personalized
    0.26
    alties
    0.26
    anyl
    0.26
    commercial
    0.26
     CUSTOM
    0.25
    _OPTS
    0.25
    ahkan
    0.25
    Activations Density 0.029%

    No Known Activations