© 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. 52956
    Prev
    Next
    INDEX
    Explanations

    "more", "less", or "most"

    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
    æĽ´
    -0.35
    交
    -0.29
    éĥ½å¾Ī
    -0.28
    æĽ´éĢĤåIJĪ
    -0.28
    é½IJ
    -0.28
    éĢĤå®ľ
    -0.27
     more
    -0.27
    æĽ´ä¸º
    -0.27
    more
    -0.26
    å¾Ī
    -0.26
    POSITIVE LOGITS
     Fully
    0.31
     fully
    0.31
    insic
    0.29
    _MAJOR
    0.28
     strength
    0.26
    ars
    0.26
    _strength
    0.25
     infl
    0.25
     Comp
    0.25
     Gron
    0.25
    Activations Density 0.007%

    No Known Activations