© 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. 22729
    Prev
    Next
    INDEX
    Explanations

    ductive

    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
    æīįè¡Į
    -0.26
     thÆ°á»Ľc
    -0.26
     holy
    -0.25
    æĸ§
    -0.25
    ç´§å¼ł
    -0.25
    minated
    -0.24
    kses
    -0.24
    åķĨ
    -0.24
    udas
    -0.24
    ä¸ªé¡¹çĽ®
    -0.24
    POSITIVE LOGITS
    igner
    0.30
     Resident
    0.28
    awning
    0.26
    è¯ģåĪ¸äº¤æĺĵ
    0.25
    mma
    0.25
    ester
    0.25
    ä¸ĢåĪĻ
    0.25
    éļĻ
    0.25
    åģļäºĭ
    0.25
     ìĦ
    0.24
    Activations Density 0.000%

    No Known Activations