© 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. 96485
    Prev
    Next
    INDEX
    Explanations

    methods and actions

    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
    è¡ĮåĬ¨
    -0.32
    _actions
    -0.30
     дейÑģÑĤвиÑı
    -0.29
    -actions
    -0.29
    ACTION
    -0.28
    CAM
    -0.28
    ninger
    -0.28
     Action
    -0.28
    Action
    -0.28
    .action
    -0.28
    POSITIVE LOGITS
     starting
    0.43
     beginning
    0.43
     home
    0.42
     other
    0.40
     whether
    0.39
     immediate
    0.37
    other
    0.36
     immediately
    0.36
     start
    0.35
     today
    0.34
    Activations Density 0.885%

    No Known Activations