© 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. 163232
    Prev
    Next
    INDEX
    Explanations

    the

    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
    åıĮçľ¼
    -0.30
    RIA
    -0.29
    çļĦçľ¼çĿĽ
    -0.28
    侬
    -0.27
    ança
    -0.26
    çľ¼æ³ª
    -0.26
    วร
    -0.25
    æĶ¯æĮģ
    -0.24
     fragile
    -0.24
     eyes
    -0.23
    POSITIVE LOGITS
    åħ¥éŨ
    0.30
     orig
    0.27
    æģ°
    0.25
     introduction
    0.25
    建
    0.25
    intro
    0.24
     Intro
    0.24
     Farrell
    0.24
    åıįæĺłåĩº
    0.24
    å¼łè´´
    0.24
    Activations Density 0.005%

    No Known Activations