© 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. 54352
    Prev
    Next
    INDEX
    Explanations

    pre

    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
     con
    -0.36
     pre
    -0.33
     w
    -0.31
     rep
    -0.30
     un
    -0.30
     middle
    -0.29
     n
    -0.28
    åħĪ
    -0.28
     pr
    -0.28
     l
    -0.28
    POSITIVE LOGITS
    åĩ¡æľ¬ç½ij
    0.34
    ord
    0.27
    æľ¬ç½ijç«Ļ
    0.26
     Logged
    0.26
     construed
    0.26
    åŁŃ
    0.25
    åĨĻåĩº
    0.24
    killer
    0.24
    éĤ£ä½į
    0.24
    å¾Īé«ĺçļĦ
    0.24
    Activations Density 0.021%

    No Known Activations