© 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. 24586
    Prev
    Next
    INDEX
    Explanations

    Start of sentence

    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
     SERIES
    -0.27
    riors
    -0.27
    *D
    -0.27
     conc
    -0.26
    _disc
    -0.25
     disc
    -0.24
    rray
    -0.24
    ué
    -0.24
    ificant
    -0.24
    æ³¢
    -0.24
    POSITIVE LOGITS
    æĪijè®°å¾Ĺ
    0.36
    请æĤ¨
    0.33
    today
    0.33
    ä»Ĭ天
    0.33
    åĽ¢
    0.32
    ä¸ĭéĿ¢æĪij们
    0.32
     hoy
    0.32
    çĤ¹åĩ»æŁ¥çľĭ
    0.30
     recounted
    0.30
    说åĪ°è¿ĻéĩĮ
    0.30
    Activations Density 0.001%

    No Known Activations