© 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. 42966
    Prev
    Next
    INDEX
    Explanations

    loop

    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
    失败
    -0.28
    ios
    -0.27
    åı¯éĿłæĢ§
    -0.25
    chy
    -0.25
    anchor
    -0.25
    âĶ¬
    -0.25
    .failure
    -0.25
    ore
    -0.24
    ä½ĵç³»
    -0.24
     surface
    -0.24
    POSITIVE LOGITS
     loop
    0.52
    Loop
    0.47
    -loop
    0.47
    loop
    0.46
     Loop
    0.45
    	loop
    0.45
    (loop
    0.44
     loops
    0.43
     looping
    0.41
    LOOP
    0.41
    Activations Density 0.012%

    No Known Activations