© 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. 8929
    Prev
    Next
    INDEX
    Explanations

    so

    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
    it
    -0.26
    ëĦIJ
    -0.26
     they
    -0.26
     no
    -0.25
     there
    -0.25
    Ùĥس
    -0.25
    _constraints
    -0.25
    å¹»
    -0.24
    éĺ¶æ®µæĢ§
    -0.23
    ÙĬÙģ
    -0.23
    POSITIVE LOGITS
     readily
    0.31
    å¥¥åľ°
    0.29
     easily
    0.29
     routinely
    0.28
     closely
    0.28
     desperately
    0.28
    trx
    0.27
    etcode
    0.27
     frequently
    0.25
    emin
    0.25
    Activations Density 0.019%

    No Known Activations