© 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. 12-TRANSCODER-HP
    7. 23707
    Prev
    Next
    INDEX
    Explanations

    dispose

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_12.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.12.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     glued
    -0.28
    åIJĮä¸Ģ个
    -0.26
    ç§ĺ书
    -0.25
    æµģæ°´
    -0.24
    éĶ¤
    -0.24
    èĥĨ
    -0.24
    Modes
    -0.24
    æĻ¡
    -0.24
    uries
    -0.24
    交
    -0.23
    POSITIVE LOGITS
    çļĦåīįæıIJä¸ĭ
    0.30
    为åħ¶
    0.28
    èĩªçĦ¶èĢĮ
    0.27
    åħ¨é¢Ŀ
    0.27
    æĭİ
    0.26
    OTP
    0.26
    pling
    0.25
    çļĦæĸ¹åIJij
    0.25
    éĻĦè¿ijçļĦ
    0.25
    éĻĦè¿ij
    0.25
    Activations Density 0.092%

    No Known Activations