© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 27-TRANSCODER-HP
    7. 57431
    Prev
    Next
    INDEX
    Explanations

    drugs, medications

    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
    Coefficient
    -0.25
    np
    -0.24
    æĮ£
    -0.24
     postData
    -0.24
    Parsed
    -0.23
    çī¢åĽºæłijç«ĭ
    -0.23
    Mage
    -0.23
    çĥĻ
    -0.23
    ,rp
    -0.23
     repost
    -0.23
    POSITIVE LOGITS
    èį¯çī©
    0.90
     drugs
    0.83
     medications
    0.81
     medication
    0.81
    èį¯
    0.73
    èĹ¥
    0.69
    èį¯åĵģ
    0.68
     antibiotics
    0.65
     drug
    0.65
    çĶ¨èį¯
    0.63
    Activations Density 0.175%

    No Known Activations