© 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. 58035
    Prev
    Next
    INDEX
    Explanations

    "correct"

    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
     known
    -0.29
     mystery
    -0.29
     mysterious
    -0.28
    vio
    -0.28
    ilinx
    -0.28
     mysteries
    -0.28
    以èī²
    -0.27
    á¹ħ
    -0.26
    ãģĤãģŁãĤĬ
    -0.26
     impossible
    -0.25
    POSITIVE LOGITS
    æŃ£ç¡®
    0.46
    Correct
    0.39
     correct
    0.38
     Correct
    0.35
    æŃ£ç¢º
    0.33
    correct
    0.32
    æŃ£ç¡®çļĦ
    0.32
    .correct
    0.30
     correctly
    0.29
    Incorrect
    0.29
    Activations Density 0.002%

    No Known Activations