© 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. 95634
    Prev
    Next
    INDEX
    Explanations

    )

    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
    anship
    -0.32
    ç»
    -0.32
     despite
    -0.31
     rehe
    -0.26
     summar
    -0.26
    ŀ
    -0.25
     IT
    -0.25
     DES
    -0.25
     MI
    -0.24
     even
    -0.24
    POSITIVE LOGITS
    éĩį
    0.28
    intro
    0.27
    女士
    0.26
    ãģĿãģ®ä»ĸ
    0.26
     minut
    0.26
    æĪijè¦ģ
    0.26
    Other
    0.26
    other
    0.25
    og
    0.25
    åŃĹæł·
    0.25
    Activations Density 0.922%

    No Known Activations