© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 12-TRANSCODER-HP
    7. 23495
    Prev
    Next
    INDEX
    Explanations

    optics

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_12.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.12.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    à¸ļรร
    -0.30
    ä¸Ģæŀ¶
    -0.29
    æ³ł
    -0.26
    æĺ¯æĢİæł·
    -0.26
    æĺ¯æĪijçļĦ
    -0.26
     brewed
    -0.25
    "He
    -0.25
    å½ĵæĹ¥
    -0.25
    coli
    -0.24
    梦è§ģ
    -0.23
    POSITIVE LOGITS
    å¤ļåľ°
    0.33
     placements
    0.32
    æīĵè¿Ľ
    0.31
     mel
    0.31
    dde
    0.29
    为æŃ¢
    0.28
    iform
    0.26
    å¡ŀ
    0.26
    çŃīå½¢å¼ı
    0.26
    æīĵåħ¥
    0.26
    Activations Density 0.000%

    No Known Activations