© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 27-TRANSCODER-HP
    7. 7894
    Prev
    Next
    INDEX
    Explanations

    thoughts

    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
    Negative Logits
    icare
    -0.31
    HostException
    -0.25
    ichern
    -0.25
    icans
    -0.25
    icolon
    -0.24
    åĽ½åĨħå¸Ĥåľº
    -0.24
    'gc
    -0.24
    ument
    -0.23
    orean
    -0.23
    æĻļ
    -0.23
    POSITIVE LOGITS
     about
    0.33
    Thought
    0.28
    ä½łæĢİä¹Ī
    0.28
    æĢĿ
    0.27
    about
    0.26
     Thoughts
    0.25
     how
    0.25
    ertext
    0.25
    妻
    0.24
    voice
    0.24
    Activations Density 0.007%

    No Known Activations