© 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. 43017
    Prev
    Next
    INDEX
    Explanations

    tubes

    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
    -0.32
    -0.31
     wire
    -0.28
    æµ·æĬ¥
    -0.27
    atar
    -0.26
    åĪ©
    -0.26
    _wire
    -0.24
    -0.24
    etag
    -0.24
    ocator
    -0.24
    POSITIVE LOGITS
    管
    0.73
    -t
    0.63
    管åĪ¶
    0.61
     tube
    0.60
     tub
    0.54
    -p
    0.53
     tubes
    0.52
     pipe
    0.51
    管çIJĨ
    0.50
    çѦ
    0.49
    Activations Density 0.020%

    No Known Activations