© 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. 30-TRANSCODER-HP
    7. 96090
    Prev
    Next
    INDEX
    Explanations

    film directors

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_30.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.30.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ulist
    -0.31
    gable
    -0.27
     laid
    -0.25
     cab
    -0.25
     treasurer
    -0.25
    amus
    -0.24
    ÑĢаÑģ
    -0.24
    è¾Ľ
    -0.24
     SUN
    -0.23
    uge
    -0.23
    POSITIVE LOGITS
     steer
    0.32
    å®ļåIJij
    0.29
     TSR
    0.29
    ä¸įèµ·
    0.27
    ente
    0.27
    æĸ¹åIJij
    0.27
     Steering
    0.26
    bery
    0.26
     Patt
    0.25
    转åIJij
    0.25
    Activations Density 0.120%

    No Known Activations