© 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. 24-TRANSCODER-HP
    7. 149957
    Prev
    Next
    INDEX
    Explanations

    sky

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_24.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.24.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Ĩµ
    -0.33
    icides
    -0.29
    ä¼łå¯¼
    -0.27
    oda
    -0.27
    ãĤªãĤ¹
    -0.26
    icide
    -0.25
    æĿĢ
    -0.24
    -addon
    -0.24
    UniqueId
    -0.24
    organic
    -0.24
    POSITIVE LOGITS
    天空
    0.52
     sky
    0.48
    æĺŁç©º
    0.39
    æĺŁæĺŁ
    0.38
    æĺŁè¾°
    0.36
     Visibility
    0.35
    æľĪ亮
    0.35
    亮度
    0.35
     visible
    0.34
     skyline
    0.34
    Activations Density 1.087%

    No Known Activations