© 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. 25419
    Prev
    Next
    INDEX
    Explanations

    situation

    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
     puck
    -0.28
    grid
    -0.26
     proper
    -0.25
     Trevor
    -0.24
    ups
    -0.24
    PTS
    -0.24
     tutors
    -0.24
     Taste
    -0.23
    ắng
    -0.23
    ustom
    -0.23
    POSITIVE LOGITS
    çļĦåľ°ä½į
    0.30
    对äºİæĪij们
    0.29
    ussen
    0.28
    çĬ¶åĨµ
    0.26
    ãĤ¤ãĥ«
    0.26
     dank
    0.26
     regarding
    0.24
    ä½Ĩæĺ¯å¯¹äºİ
    0.24
    æīĭèĦļ
    0.24
     forced
    0.23
    Activations Density 0.018%

    No Known Activations