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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 23-TRANSCODER-HP
    7. 163384
    Prev
    Next
    INDEX
    Explanations

    Digits

    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
    çݯå¢ĥä¸Ń
    -0.34
    ãĥ¼ãĥł
    -0.29
     hourly
    -0.27
     embargo
    -0.26
     alternating
    -0.26
    æ°¸ä¸į
    -0.25
     epoch
    -0.25
     microscopy
    -0.25
    adir
    -0.25
     altern
    -0.25
    POSITIVE LOGITS
    å¦Ħ
    0.30
     Sonic
    0.28
     Ton
    0.28
    æ·ĭ
    0.27
    gas
    0.27
    éĥ½åľ¨
    0.26
    åĽ½æ°ij
    0.26
     Clim
    0.26
    esson
    0.26
    Ton
    0.26
    Activations Density 0.034%

    No Known Activations