© 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. 150544
    Prev
    Next
    INDEX
    Explanations

    wind

    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
     gam
    -0.29
    (ml
    -0.28
    èģĮ
    -0.27
     Gam
    -0.26
    ret
    -0.26
    lösung
    -0.26
    åıįåºĶ
    -0.26
    ML
    -0.26
    迹
    -0.26
    ihar
    -0.25
    POSITIVE LOGITS
    quals
    0.27
    gee
    0.25
    -metadata
    0.25
    UMB
    0.25
    wind
    0.25
     winds
    0.25
     fra
    0.24
    空æ°Ķè´¨éĩı
    0.24
    天æ°Ķ
    0.24
    weather
    0.24
    Activations Density 0.918%

    No Known Activations