© 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. 57320
    Prev
    Next
    INDEX
    Explanations

    corrections

    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
    æĭ´
    -0.29
    亮
    -0.26
     stealing
    -0.26
     spared
    -0.26
     supreme
    -0.26
    _MT
    -0.25
     steal
    -0.25
    achinery
    -0.25
    _strike
    -0.25
    arker
    -0.25
    POSITIVE LOGITS
    磫
    0.57
     correction
    0.56
    磫æŃ£
    0.55
     Correction
    0.50
    çºłæŃ£
    0.50
     corrections
    0.49
     correcting
    0.45
     corrected
    0.44
     Corrections
    0.44
     corrective
    0.42
    Activations Density 0.002%

    No Known Activations