© 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. 33-TRANSCODER-HP
    7. 53084
    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_33.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.33.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    :\"
    -0.28
     )↵
    -0.27
     keep
    -0.26
    ”
    -0.25
    lop
    -0.25
     )"
    -0.25
     Gos
    -0.24
     transports
    -0.24
    ãĢĥ
    -0.24
    “
    -0.24
    POSITIVE LOGITS
    %.
    0.47
    ;.
    0.45
     %.
    0.43
     $.
    0.42
    !.
    0.41
    |.
    0.40
    ãĢij,
    0.40
    -.
    0.39
     ?.
    0.39
    %.↵↵
    0.39
    Activations Density 0.025%

    No Known Activations