© 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. 27-TRANSCODER-HP
    7. 8415
    Prev
    Next
    INDEX
    Explanations

    will

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_27.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.27.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     themselves
    -0.49
    ç»ĻæĪij们
    -0.36
    æĪij们就
    -0.36
    æĺ¯æĪij们
    -0.35
    æĪijä»¬åľ¨
    -0.35
    为æĪij们
    -0.35
     thems
    -0.34
    æĪij们åı¯ä»¥
    -0.32
    æĪijä»¬ä¹Ł
    -0.32
    èį¦
    -0.32
    POSITIVE LOGITS
     need
    0.33
     suspect
    0.28
     Probably
    0.28
    TPL
    0.26
    Probably
    0.26
     probably
    0.25
     NEED
    0.25
    æĦŁåıĹåĪ°
    0.25
     hears
    0.25
     Zwe
    0.25
    Activations Density 0.029%

    No Known Activations