© 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. 108402
    Prev
    Next
    INDEX
    Explanations

    she

    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
     says
    -0.52
    说çļĦæĺ¯
    -0.50
    æĸĩä¸Ń
    -0.50
     mentions
    -0.49
     description
    -0.48
     mention
    -0.47
     stated
    -0.47
    æıIJåĪ°
    -0.47
    æııè¿°
    -0.45
    é¢ĺ缮
    -0.45
    POSITIVE LOGITS
    Ñĩин
    0.29
    лÑİд
    0.26
    ÑĥниÑĨип
    0.24
    strategy
    0.23
    uru
    0.23
    ares
    0.23
     ensuring
    0.23
    hiro
    0.23
     anticipating
    0.23
    åīįèĢħ
    0.23
    Activations Density 0.937%

    No Known Activations