© 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. 8381
    Prev
    Next
    INDEX
    Explanations

    medical/technical documents

    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
    è¿ĩåĪĨ
    -0.28
    éģį
    -0.28
    omat
    -0.27
    èѦæĥķ
    -0.26
    æĥ¯
    -0.26
     insecure
    -0.26
    UTH
    -0.26
    æĴŀåĩ»
    -0.25
    æģIJ
    -0.25
    åĬłåī§
    -0.25
    POSITIVE LOGITS
    corev
    0.26
     formulations
    0.26
    åĽ·
    0.26
    tracts
    0.26
    anyl
    0.25
    yt
    0.25
    yll
    0.24
     itemCount
    0.24
     pleas
    0.24
    AMPL
    0.24
    Activations Density 0.010%

    No Known Activations