© 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. 8653
    Prev
    Next
    INDEX
    Explanations

    technical language

    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
    éĽĢ
    -0.28
     sound
    -0.26
    orp
    -0.26
     DateTimeKind
    -0.25
    çŁ¢
    -0.24
    rium
    -0.24
    /apis
    -0.24
    inka
    -0.24
    çļĦäºĭå®ŀ
    -0.24
    ernote
    -0.23
    POSITIVE LOGITS
     launder
    0.30
     runaway
    0.27
    leaning
    0.27
    åŁ¹åħ»
    0.27
    uring
    0.26
    械
    0.26
    ständ
    0.25
    æĬĽ
    0.25
    lauf
    0.24
     unwanted
    0.23
    Activations Density 0.009%

    No Known Activations