© 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. 95478
    Prev
    Next
    INDEX
    Explanations

    technical documentation/CAD/CAM

    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
    imore
    -0.30
     metavar
    -0.27
     Cit
    -0.25
    леÑĤ
    -0.25
     shell
    -0.25
    doors
    -0.25
    Delta
    -0.25
    èī¯
    -0.24
     delta
    -0.24
    é¢ĺ主
    -0.23
    POSITIVE LOGITS
    æĭĶ
    0.36
     Inventory
    0.27
    icularly
    0.27
    æĭĤ
    0.26
    alyze
    0.26
    æĬľãģij
    0.26
    ynes
    0.24
    éĤĵå°ı
    0.24
    bucks
    0.24
    ä¼ij
    0.24
    Activations Density 0.884%

    No Known Activations