© 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. 57913
    Prev
    Next
    INDEX
    Explanations

    depend

    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
    ķĮ
    -0.29
    è°ª
    -0.28
    å½»
    -0.28
     comun
    -0.27
    æį£
    -0.27
     commun
    -0.26
    ãĤ§
    -0.26
    ç´«å¤ĸ
    -0.25
    rror
    -0.24
    ECH
    -0.24
    POSITIVE LOGITS
    ä¾Ŀèµĸ
    0.93
     dependence
    0.90
     dependency
    0.82
     depend
    0.79
     dependent
    0.78
     Depend
    0.78
     dependencies
    0.75
    dependence
    0.73
    depend
    0.71
     Dependency
    0.70
    Activations Density 0.000%

    No Known Activations