© 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. 27-TRANSCODER-HP
    7. 56639
    Prev
    Next
    INDEX
    Explanations

    4

    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
    jee
    -0.30
    å§Ķç»Ħç»ĩ
    -0.28
    eness
    -0.27
    simulate
    -0.26
    ä¸ĭåįĬå¹´
    -0.25
     domest
    -0.25
     Investigation
    -0.24
     died
    -0.24
    ç»Ĩç»Ĩ
    -0.24
    tgt
    -0.24
    POSITIVE LOGITS
    å®Į
    0.34
    otions
    0.28
     press
    0.27
     Äij
    0.27
    igen
    0.25
    æij¸
    0.25
     surrender
    0.24
     Press
    0.24
    ogo
    0.24
    éĹ·
    0.24
    Activations Density 0.002%

    No Known Activations