© 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. 53981
    Prev
    Next
    INDEX
    Explanations

    art

    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
    art
    -0.36
     art
    -0.35
     Art
    -0.34
    -art
    -0.34
    Art
    -0.33
    èīºæľ¯
    -0.32
    ART
    -0.32
    _art
    -0.31
    èĹĿè¡ĵ
    -0.30
     ART
    -0.29
    POSITIVE LOGITS
    hower
    0.29
    iser
    0.27
     :-)
    0.25
    æĺ¾çİ°
    0.25
    å±ıå¹ķä¸Ĭ
    0.25
    rollable
    0.24
    æĺ¾ç¤º
    0.24
     Tech
    0.24
    aped
    0.23
    (Optional
    0.23
    Activations Density 0.013%

    No Known Activations