© 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. 163429
    Prev
    Next
    INDEX
    Explanations

    Code/technical writing 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
     exits
    -0.27
    raw
    -0.26
     arc
    -0.26
    RAW
    -0.26
    åľ¨ä»ĸçļĦ
    -0.25
    SEE
    -0.25
    åIJ¦
    -0.24
    ова
    -0.24
    Raw
    -0.24
     Tut
    -0.24
    POSITIVE LOGITS
    è¿Ļæł·ä¸Ģ
    0.28
     hence
    0.27
    jab
    0.26
    æĦŁæħ¨
    0.26
    åĽłæѤ
    0.25
    æĦŁåı¹
    0.25
     thus
    0.25
    izer
    0.25
    æīĢ以
    0.24
    çĶ±æѤåı¯è§ģ
    0.24
    Activations Density 0.001%

    No Known Activations