© 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. 57795
    Prev
    Next
    INDEX
    Explanations

    names

    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
     anthrop
    -0.56
     Anthrop
    -0.51
    Anth
    -0.50
     anthropology
    -0.47
    人é¡ŀ
    -0.43
    人类
    -0.42
     ethn
    -0.41
    anth
    -0.40
     anth
    -0.34
     Anth
    -0.34
    POSITIVE LOGITS
    peror
    0.29
    åĨ·
    0.25
     Led
    0.25
     lòng
    0.24
    atta
    0.24
    Led
    0.24
     actionable
    0.23
     bargaining
    0.23
    aura
    0.23
    ako
    0.23
    Activations Density 0.003%

    No Known Activations