© 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. 20-TRANSCODER-HP
    7. 130230
    Prev
    Next
    INDEX
    Explanations

    beginnings and time periods

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_20.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.20.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    å¼Ģå§ĭ
    -0.42
    å¹´å¼Ģå§ĭ
    -0.40
    æľĢæĹ©
    -0.39
    æľĢæĹ©çļĦ
    -0.38
    å°±å¼Ģå§ĭ
    -0.37
    æľĢä½İ
    -0.37
     beginnings
    -0.36
     Begin
    -0.34
    éĸĭå§ĭ
    -0.34
     thresholds
    -0.32
    POSITIVE LOGITS
     remaining
    0.27
    éĺ³åĮº
    0.27
    plets
    0.26
     complement
    0.25
    ä¸Ģ段æŶéĹ´
    0.25
    à¸ĵะ
    0.25
    rell
    0.25
     yans
    0.24
    wi
    0.24
    ä¸įåIJĪæł¼
    0.24
    Activations Density 54.405%

    No Known Activations