© 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. 95859
    Prev
    Next
    INDEX
    Explanations

    of

    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
    ÑĪиÑĢ
    -0.27
    çŃĶ
    -0.26
     Dispatch
    -0.26
    ÑĦоÑĢ
    -0.25
    æµ®
    -0.25
    isel
    -0.24
     department
    -0.24
    (nb
    -0.24
     Sachs
    -0.23
     warnings
    -0.23
    POSITIVE LOGITS
     Roll
    0.28
    anela
    0.28
    aret
    0.27
     roll
    0.27
     Schumer
    0.26
    模
    0.26
    éĿ¢
    0.26
    QUENCE
    0.25
     Face
    0.25
    ä¸ĭéĿ¢æĺ¯å°ı
    0.24
    Activations Density 0.917%

    No Known Activations