© 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. 96238
    Prev
    Next
    INDEX
    Explanations

    technical descriptions

    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
    ä¸įåıĬ
    -0.29
    ä¸įå¦Ĥ
    -0.28
    zza
    -0.27
    fel
    -0.26
    æľª
    -0.25
     fle
    -0.25
    %p
    -0.25
     Perf
    -0.25
    htable
    -0.24
    çģ«è½¦
    -0.24
    POSITIVE LOGITS
     effective
    0.42
    effective
    0.38
    æľīæķĪ
    0.38
     Effective
    0.36
    æľīæķĪçļĦ
    0.35
    Effective
    0.35
    -effective
    0.34
    çļĦæľīæķĪ
    0.34
     ÑįÑĦÑĦекÑĤив
    0.31
    æľīæķĪæĢ§
    0.26
    Activations Density 0.882%

    No Known Activations