© 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. 27-TRANSCODER-HP
    7. 56848
    Prev
    Next
    INDEX
    Explanations

    soon

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_27.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.27.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    æĹ©å°±
    -0.34
    æĹ©å·²
    -0.31
     sooner
    -0.30
    æĹ©åľ¨
    -0.30
    ynchronously
    -0.30
    æĹ©
    -0.30
    æıIJåīį
    -0.28
    ç»´æĬ¤
    -0.28
    ATIO
    -0.27
    ç»´æĮģ
    -0.27
    POSITIVE LOGITS
     enough
    0.72
    Enough
    0.51
     Enough
    0.49
    ened
    0.31
    entimes
    0.29
     sufficient
    0.29
    è¶³å¤ŁçļĦ
    0.28
    å¤ł
    0.27
    itudes
    0.27
    aden
    0.27
    Activations Density 0.013%

    No Known Activations