© 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. 53703
    Prev
    Next
    INDEX
    Explanations

    Follows proper names

    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
    ighted
    -0.29
     indirect
    -0.26
    é»İæĺİ
    -0.25
    erald
    -0.25
    icity
    -0.25
    çĶµè¯Ŀ
    -0.25
    isex
    -0.24
    èĽĶ
    -0.24
     thủ
    -0.24
    æķ
    -0.23
    POSITIVE LOGITS
    ìĹ´
    0.31
    rick
    0.29
    oop
    0.27
    rete
    0.26
    æĭŁ
    0.26
     Cour
    0.25
    åľĪ
    0.25
    èĵī
    0.25
    oller
    0.24
    otron
    0.24
    Activations Density 0.008%

    No Known Activations