© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 23-TRANSCODER-HP
    7. 163105
    Prev
    Next
    INDEX
    Explanations

    only

    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
    è·¯è¿ĩ
    -0.28
    ne
    -0.28
     nond
    -0.27
    æķij人
    -0.27
    NU
    -0.26
     standby
    -0.26
     bothering
    -0.25
    éĺ²åį«
    -0.25
     bother
    -0.25
     refer
    -0.24
    POSITIVE LOGITS
    çİ°åľ¨çļĦ
    0.34
     now
    0.32
    çİ°åľ¨å·²ç»ı
    0.32
     NOW
    0.31
    çİ°åľ¨
    0.31
    (now
    0.31
    now
    0.30
    [now
    0.30
    ãĤĪãģĨãģ«ãģªãĤĬãģ¾ãģĹãģŁ
    0.30
    æĪijçİ°åľ¨
    0.29
    Activations Density 0.002%

    No Known Activations