© 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. 23-TRANSCODER-HP
    7. 24798
    Prev
    Next
    INDEX
    Explanations

    "always" and code snippets

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_23.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.23.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    å¹²åĩĢ
    -0.29
    tic
    -0.26
    æĽ´éĩįè¦ģ
    -0.25
    reas
    -0.25
    (pad
    -0.25
    íĭ±
    -0.24
    é«ĺæķĪ
    -0.24
     poz
    -0.24
    åīįçŀ»
    -0.24
    æ¸ħæĻ°
    -0.24
    POSITIVE LOGITS
     ngũ
    0.27
    åŃĺåľ¨ä¸Ģå®ļ
    0.26
    åı¯èĥ½åŃĺåľ¨
    0.26
    bö
    0.25
    ä¸įèī¯
    0.25
    (Size
    0.25
    人çĶŁçļĦ
    0.25
     somewhere
    0.24
    æĸ¯åĿ¦
    0.24
    oner
    0.23
    Activations Density 0.001%

    No Known Activations