© 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. 35-TRANSCODER-HP
    7. 40052
    Prev
    Next
    INDEX
    Explanations

    essential

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_35.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.35.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     for
    -0.67
    for
    -0.66
    For
    -0.56
    -for
    -0.55
    _for
    -0.49
    1
    -0.48
     For
    -0.47
     FOR
    -0.46
    	for
    -0.45
    2
    -0.44
    POSITIVE LOGITS
    à¹Ĥà¸Ķยà¹Ģà¸īà¸ŀาะ
    0.29
    æĥħç·Ĵ
    0.27
     importância
    0.26
     zupeÅĤnie
    0.25
     çalÄ±ÅŁmaları
    0.25
     powsta
    0.25
     gücü
    0.24
     krótk
    0.24
     sá»±
    0.24
    åĩĨå¤ĩå·¥ä½ľ
    0.24
    Activations Density 7.951%

    No Known Activations