© 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. 22607
    Prev
    Next
    INDEX
    Explanations

    forged

    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
    uters
    -0.29
    itat
    -0.26
    æĶ¶å½ķ
    -0.26
     trace
    -0.26
    çłĶ究ä¸Ńå¿ĥ
    -0.25
    æĸĩåŃĹ
    -0.24
    å¡Ķ
    -0.24
    /custom
    -0.23
     diagn
    -0.23
    uth
    -0.23
    POSITIVE LOGITS
    евиÑĩ
    0.32
    iete
    0.27
    mue
    0.25
    mares
    0.25
    onis
    0.24
     Chá»ĭ
    0.24
    mdir
    0.24
    аÑĩ
    0.24
    èĥĮä¸Ĭ
    0.24
     appetite
    0.24
    Activations Density 0.001%

    No Known Activations