© 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. 162152
    Prev
    Next
    INDEX
    Explanations

    Measurement units (meters, centimeters)

    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
    aldo
    -0.32
    hiba
    -0.28
    lóg
    -0.27
    mere
    -0.25
    nü
    -0.24
    ream
    -0.24
    cope
    -0.24
    inka
    -0.24
    uvo
    -0.24
     obvious
    -0.24
    POSITIVE LOGITS
    ington
    0.29
    çŃĸ
    0.27
    icorn
    0.24
    Gran
    0.24
    ularity
    0.24
    ä¸Ģ
    0.24
    ä¸ĢèĦļ
    0.24
    åĪºæ¿Ģ
    0.24
    ä¸īçĤ¹
    0.23
    Loc
    0.23
    Activations Density 0.019%

    No Known Activations