© 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. 162461
    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
     contr
    -0.28
    **
    -0.27
     same
    -0.25
    åĨ°ç®±
    -0.25
    zych
    -0.24
    åIJĮä¸Ģ
    -0.24
    prit
    -0.24
    人æ°ijå¸ģ
    -0.23
     backup
    -0.23
    ~
    -0.23
    POSITIVE LOGITS
    rift
    0.27
    çļĦ形象
    0.26
    IClient
    0.26
     Og
    0.25
    åī¯å¸Ĥéķ¿
    0.25
    確å®ļ
    0.25
    enuity
    0.25
    uide
    0.24
    locale
    0.24
    brace
    0.24
    Activations Density 0.002%

    No Known Activations