© 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. 32-TRANSCODER-HP
    7. 42804
    Prev
    Next
    INDEX
    Explanations

    often

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_32.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.32.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    å®
    -0.31
    alm
    -0.25
    обÑīе
    -0.24
    éģĵ士
    -0.24
    oons
    -0.23
    ä¸įåIJĮç±»åŀĭ
    -0.23
     quoi
    -0.23
    è¯ķåį·
    -0.23
     appar
    -0.23
    onso
    -0.23
    POSITIVE LOGITS
     prove
    0.47
     referred
    0.46
     refer
    0.44
     proven
    0.42
     proved
    0.42
    refer
    0.40
     described
    0.40
     describe
    0.38
     proves
    0.38
    prove
    0.37
    Activations Density 0.019%

    No Known Activations