© 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. 54106
    Prev
    Next
    INDEX
    Explanations

    Descriptions of arts/crafts

    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
     Artist
    -0.32
    Artist
    -0.32
    artist
    -0.30
    ä¸īæĸ¹
    -0.29
    èIJ½ä¸ĭ
    -0.28
     artist
    -0.28
    DNS
    -0.28
    Designer
    -0.27
    èīºæľ¯
    -0.26
    lege
    -0.25
    POSITIVE LOGITS
     clocks
    0.32
     clock
    0.32
    éĴŁ
    0.29
    輯
    0.29
     tape
    0.29
     kim
    0.29
    clock
    0.27
    agine
    0.27
     masks
    0.26
     belts
    0.25
    Activations Density 0.026%

    No Known Activations