© 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. 25-TRANSCODER-HP
    7. 108014
    Prev
    Next
    INDEX
    Explanations

    continue

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_25.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.25.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    è¿ĺåİŁ
    -0.25
     ÑģебÑı
    -0.25
    éĶµ
    -0.25
    기ê°Ģ
    -0.25
     multis
    -0.24
     PLA
    -0.24
    ounder
    -0.24
    åĬ²
    -0.23
    Mapper
    -0.23
     jackets
    -0.23
    POSITIVE LOGITS
    åĪ°æľĢåIJİ
    0.39
    åĪ°
    0.32
     to
    0.30
    æĹ¥èĩ³
    0.29
    odox
    0.27
    tog
    0.27
    ä¸įæĸŃçļĦ
    0.26
    edList
    0.26
     onward
    0.26
    /../
    0.25
    Activations Density 1.093%

    No Known Activations