© 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. 56770
    Prev
    Next
    INDEX
    Explanations

    code and links

    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
     spoil
    -0.27
    èĢIJ
    -0.27
    éĿ¢
    -0.27
     plural
    -0.26
    -face
    -0.26
    èĤī
    -0.26
     dare
    -0.25
    -ed
    -0.25
    omet
    -0.25
    解
    -0.25
    POSITIVE LOGITS
    rone
    0.31
    ruk
    0.29
    riba
    0.27
    $__
    0.27
     Gesch
    0.27
     scrub
    0.26
    çİĩè¾¾åĪ°
    0.26
    è¿Ļä¹Īå¤ļå¹´
    0.25
    distributed
    0.25
    ä¸ĭæīĭ
    0.25
    Activations Density 0.000%

    No Known Activations