© 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. 25477
    Prev
    Next
    INDEX
    Explanations

    medical/biological issues

    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
     Truth
    -0.26
    å±ŀå®ŀ
    -0.25
    omorphic
    -0.25
    fact
    -0.25
     Complete
    -0.25
    nell
    -0.24
    å®īå±ħ
    -0.24
    èĤī
    -0.24
     complete
    -0.24
    ä½ľä¸ºä¸Ģç§į
    -0.24
    POSITIVE LOGITS
    çļĦå°±æĺ¯
    0.28
     downstairs
    0.26
    uktur
    0.25
    èħ»
    0.25
     showError
    0.25
    èķĻ
    0.25
    itage
    0.24
     offending
    0.24
    PLUGIN
    0.24
     fir
    0.24
    Activations Density 0.002%

    No Known Activations