© 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. 96081
    Prev
    Next
    INDEX
    Explanations

    backyards

    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
     Horde
    -0.28
     permalink
    -0.27
    ä½İè¿·
    -0.25
     Horizon
    -0.25
    éĺĸ
    -0.24
    æĬķæĶ¾
    -0.24
    æĶ¾æīĭ
    -0.24
     Nordic
    -0.24
     Domain
    -0.23
     Namespace
    -0.23
    POSITIVE LOGITS
     mounting
    0.29
    ç¾İ
    0.27
    dam
    0.26
    fuse
    0.25
     binding
    0.25
    æĬ¥è®°èĢħ
    0.25
    stitial
    0.25
    ervice
    0.25
    mount
    0.24
     superf
    0.24
    Activations Density 0.883%

    No Known Activations