© 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. 32-TRANSCODER-HP
    7. 41031
    Prev
    Next
    INDEX
    Explanations

    drug use

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_32.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.32.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    utions
    -0.28
    æ¯ĵ
    -0.27
     Alta
    -0.27
     Haut
    -0.26
    idot
    -0.25
     Cunningham
    -0.24
     ground
    -0.24
    isObject
    -0.24
     disap
    -0.24
    MITTED
    -0.24
    POSITIVE LOGITS
    drug
    0.33
    Drug
    0.30
     drug
    0.28
     Drug
    0.28
    å¹²
    0.27
    æĢĴ
    0.26
    DR
    0.26
    ores
    0.26
    oe
    0.26
    VS
    0.25
    Activations Density 0.004%

    No Known Activations