© 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. 42813
    Prev
    Next
    INDEX
    Explanations

    parenthesis and brackets

    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
    edly
    -0.30
    rape
    -0.26
    itchens
    -0.25
    æ¯ĶèµĽä¸Ń
    -0.25
     whistle
    -0.25
    æ°¸ä¹ħ
    -0.25
    ANA
    -0.24
    semb
    -0.24
     déc
    -0.24
    orth
    -0.23
    POSITIVE LOGITS
    ))*(
    0.43
    ])[
    0.42
    ])*
    0.39
    ])(
    0.38
    )][
    0.35
    '])[
    0.35
    ))(
    0.34
    ]][
    0.34
    ))[
    0.34
    ))/(
    0.34
    Activations Density 0.024%

    No Known Activations