© 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. 32-TRANSCODER-HP
    7. 42332
    Prev
    Next
    INDEX
    Explanations

    technical language

    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
    Not in Any Lists

    No Comments

    Negative Logits
    æħ¢æħ¢åľ°
    -0.28
    两个人
    -0.25
    craft
    -0.25
    rather
    -0.25
    osi
    -0.25
    -Sah
    -0.24
    åĪ®
    -0.24
     Marino
    -0.23
     communicator
    -0.23
    -dark
    -0.23
    POSITIVE LOGITS
     particular
    0.49
     specific
    0.44
     different
    0.43
    ä¸įåIJĮçļĦ
    0.40
     special
    0.39
    pecific
    0.38
     distinct
    0.37
     a
    0.37
    çī¹å®ļ
    0.35
    çī¹åĪ«
    0.35
    Activations Density 0.000%

    No Known Activations