© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 23-TRANSCODER-HP
    7. 23408
    Prev
    Next
    INDEX
    Explanations

    effects and applications

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_23.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.23.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    aly
    -0.32
    ÑģÑĤи
    -0.26
    eln
    -0.25
    anio
    -0.25
     Jenner
    -0.25
    æĸ½
    -0.24
     inaccessible
    -0.24
    pwd
    -0.24
    pler
    -0.24
    Specification
    -0.24
    POSITIVE LOGITS
    å¹²ä»Ģä¹Ī
    0.33
    为ä»Ģä¹Īä¼ļ
    0.31
    为ä½ķ
    0.29
    æĢİä¹Īçľĭ
    0.28
    为åķ¥
    0.27
    æĢİä¹ĪåĬŀ
    0.27
    oken
    0.27
    haft
    0.26
    为ä»Ģä¹Īä¸į
    0.26
    rement
    0.26
    Activations Density 0.033%

    No Known Activations