© 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. 57044
    Prev
    Next
    INDEX
    Explanations

    first event

    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
     immediately
    -0.76
     quickly
    -0.71
    ç«ĭåį³
    -0.70
    ç«ĭåĪ»
    -0.69
     promptly
    -0.67
     instantly
    -0.65
     immediate
    -0.65
     Immediately
    -0.64
    Immediately
    -0.63
    Immediate
    -0.60
    POSITIVE LOGITS
     completion
    0.33
    omo
    0.31
    æĬķ产
    0.31
    æĬµè¾¾
    0.30
     Completion
    0.30
    fld
    0.29
    建æĪIJ
    0.29
    åĪ°è¾¾
    0.29
    å®ĮæĪIJ
    0.29
    aira
    0.28
    Activations Density 0.000%

    No Known Activations