© 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. 39464
    Prev
    Next
    INDEX
    Explanations

    comparisons

    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
     than
    -1.70
    than
    -1.55
    Than
    -1.48
     Than
    -1.46
    -than
    -1.30
     THAN
    -1.27
    _than
    -1.16
    _THAN
    -0.94
     niż
    -0.82
    /blob
    -0.82
    POSITIVE LOGITS
    就好
    0.30
    便ä¼ļ
    0.28
    åIJĦå¼ı
    0.28
    å¾Īæĸ¹ä¾¿
    0.28
    就没
    0.27
    å°±å¿ħé¡»
    0.27
    æĪĸèĢħåħ¶ä»ĸ
    0.27
    åľ¨åĵª
    0.27
     vicious
    0.27
    å°±åĥıæĺ¯
    0.26
    Activations Density 4.787%

    No Known Activations