© 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. 163820
    Prev
    Next
    INDEX
    Explanations

    varied document excerpts

    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
    æīĩ
    -0.27
    é¢ĺæĿIJ
    -0.26
     rel
    -0.26
    oul
    -0.25
    cms
    -0.25
     slipped
    -0.24
    ov
    -0.24
    åľ¨è¿ĩåİ»
    -0.24
    ç³ķ
    -0.24
    ONO
    -0.24
    POSITIVE LOGITS
     prerequisites
    0.27
    equality
    0.25
    upp
    0.25
     prerequisite
    0.25
    emics
    0.24
    æłĩéħį
    0.24
    tha
    0.24
    æĸ°æ¬¾
    0.23
    æĽ´éĩįè¦ģçļĦ
    0.23
    -application
    0.23
    Activations Density 0.002%

    No Known Activations