© 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. 9139
    Prev
    Next
    INDEX
    Explanations

    science and engineering

    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
    itution
    -0.28
    Æ°u
    -0.26
     Phelps
    -0.26
    handling
    -0.26
    æĢİä¹Īçľĭ
    -0.25
    /display
    -0.25
     Display
    -0.25
     Kou
    -0.24
    éĹ²
    -0.24
    elps
    -0.24
    POSITIVE LOGITS
    åݨ
    0.30
     mechanical
    0.30
     engines
    0.30
     Engine
    0.29
     engine
    0.28
     princip
    0.27
    é£İæīĩ
    0.27
     mechanically
    0.26
    onDelete
    0.26
    erator
    0.26
    Activations Density 0.001%

    No Known Activations