© 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. 22770
    Prev
    Next
    INDEX
    Explanations

    Rosenberg

    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
    æĪĹ
    -0.28
    lein
    -0.27
    ä¸įåı¯
    -0.25
    èµ·äºĨ
    -0.25
     Im
    -0.25
     immer
    -0.25
    çłĶ
    -0.25
    pler
    -0.24
    quir
    -0.24
     ev
    -0.24
    POSITIVE LOGITS
    -care
    0.28
    eam
    0.26
    earing
    0.26
    æľªæĿ¥çļĦ
    0.25
     Verb
    0.25
    care
    0.25
    涯
    0.25
    UTURE
    0.25
    Future
    0.25
    åĪ¶åº¦æĶ¹éĿ©
    0.25
    Activations Density 0.001%

    No Known Activations