© 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. 162593
    Prev
    Next
    INDEX
    Explanations

    These/This

    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
     GANG
    -0.29
    WithMany
    -0.28
    stag
    -0.27
     ë¬¼ë¡ł
    -0.27
    sec
    -0.26
    æľīä¸įå°ij
    -0.26
    (locations
    -0.26
    è·¯çĶ±
    -0.25
    çĬ¬
    -0.25
    oce
    -0.25
    POSITIVE LOGITS
     satur
    0.28
    yscale
    0.27
    oval
    0.26
     siege
    0.26
     balls
    0.25
     (:
    0.25
     finished
    0.25
    æ²Ļé¾Ļ
    0.25
    ä¸Ģ线
    0.25
     dés
    0.25
    Activations Density 0.005%

    No Known Activations