© 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. 24-TRANSCODER-HP
    7. 149728
    Prev
    Next
    INDEX
    Explanations

    limited

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_24.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.24.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    æĴ®
    -0.24
    Æ°u
    -0.24
     FOREIGN
    -0.24
    å¸ģ
    -0.23
    æĭį
    -0.23
    ÙĪرÙĪ
    -0.23
    cia
    -0.23
    uvo
    -0.23
    oney
    -0.23
    é¹Ń
    -0.23
    POSITIVE LOGITS
    çĵ¶é¢Ī
    0.29
    lems
    0.28
    obuf
    0.27
     incons
    0.24
     penetr
    0.23
    纸ä¸Ĭ
    0.23
    è®¤çľŁåŃ¦ä¹ł
    0.23
    ·»
    0.23
    åħ¬è®¤çļĦ
    0.23
    追éļı
    0.23
    Activations Density 0.940%

    No Known Activations