© 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. 95990
    Prev
    Next
    INDEX
    Explanations

    Data and coding

    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
     vit
    -0.37
    æĹĭ转
    -0.29
    ital
    -0.28
     transforming
    -0.27
     Rot
    -0.26
    isy
    -0.26
     Vit
    -0.26
    itation
    -0.26
     Sag
    -0.26
     displ
    -0.25
    POSITIVE LOGITS
     deriv
    0.29
    åĢĴ
    0.29
    åıijå±ķéĺ¶æ®µ
    0.28
    sand
    0.28
    лик
    0.27
    æĪª
    0.26
    çłĤ
    0.25
    æıIJæ¡Ī
    0.25
    beck
    0.25
    åij½é¢ĺ
    0.25
    Activations Density 0.882%

    No Known Activations