© 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. 31-TRANSCODER-HP
    7. 18675
    Prev
    Next
    INDEX
    Explanations

    say ")

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_31.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.31.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    urities
    -0.27
    >>()
    -0.26
     onLoad
    -0.24
    icolon
    -0.24
     flush
    -0.24
    åĶĽ
    -0.23
    orks
    -0.23
    åı¯ä»¥å¸®åĬ©
    -0.23
     disemb
    -0.23
    /]
    -0.23
    POSITIVE LOGITS
    ).
    0.38
    }.
    0.29
    ").
    0.29
    ).^
    0.28
    ).↵
    0.28
    ï¼īãĢĤ
    0.27
    alcon
    0.27
    )./
    0.27
     Chamber
    0.26
    "].
    0.26
    Activations Density 0.963%

    No Known Activations