© 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. 30-TRANSCODER-HP
    7. 95694
    Prev
    Next
    INDEX
    Explanations

    Legal documents

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_30.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.30.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    éĢĸ
    -0.27
    haul
    -0.27
    cover
    -0.27
     nast
    -0.26
     streams
    -0.25
    æķĻèĤ²éĥ¨
    -0.25
     Instructions
    -0.25
    IODevice
    -0.24
     Filed
    -0.24
     Streams
    -0.24
    POSITIVE LOGITS
     âĸĪ
    0.26
     Dek
    0.26
     Spart
    0.26
    蹦
    0.25
    mour
    0.25
     ble
    0.25
    èĤĥ
    0.24
    èį¡
    0.24
    üns
    0.24
    pii
    0.24
    Activations Density 0.071%

    No Known Activations