© 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. 163325
    Prev
    Next
    INDEX
    Explanations

    how

    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
    å°ij
    -0.28
    çĬ¹
    -0.27
     nhiên
    -0.26
    \E
    -0.24
    æĢİ
    -0.24
     equitable
    -0.24
    Equip
    -0.23
    vÃŃ
    -0.23
     lá»ĩ
    -0.23
    éĢĶ
    -0.23
    POSITIVE LOGITS
    åĽ¢
    0.29
    æ´¾
    0.26
    part
    0.25
    åĬĪ
    0.25
    bett
    0.25
    fort
    0.25
    ARAM
    0.24
    èı©æıIJ
    0.24
    æľīèī²
    0.24
    appearance
    0.24
    Activations Density 0.004%

    No Known Activations