© 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. 57852
    Prev
    Next
    INDEX
    Explanations

    non

    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
    inheritDoc
    -0.26
    ä¼ĺç§Ģ
    -0.26
    кÑĢÑĭ
    -0.26
    æĸ¹åı¯
    -0.26
    MIT
    -0.25
    porter
    -0.25
    èµĦæºIJåħ±äº«
    -0.25
    Sharper
    -0.24
    Hints
    -0.24
    bung
    -0.24
    POSITIVE LOGITS
     Zwe
    0.29
     actions
    0.27
     governmental
    0.27
     sadd
    0.27
     Actions
    0.26
     dint
    0.26
    asso
    0.26
    åĪ¶åº¦
    0.26
    Actions
    0.26
     institutions
    0.25
    Activations Density 0.011%

    No Known Activations