© 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. 8904
    Prev
    Next
    INDEX
    Explanations

    have

    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
    åĪĩæį¢
    -0.29
    羣çļ®
    -0.28
     Ev
    -0.26
     longer
    -0.25
    å±ĭéĩĮ
    -0.24
     synthetic
    -0.24
     Longer
    -0.23
    à¸Ĺà¸Ńà¸Ķ
    -0.23
     lengths
    -0.23
    (vars
    -0.23
    POSITIVE LOGITS
     also
    0.29
    irate
    0.28
    dings
    0.28
     indirectly
    0.28
     am
    0.27
    éĴŃ
    0.27
    ä¹Łä¸º
    0.27
    ateur
    0.27
    éĹ´æİ¥
    0.27
     ÑĤоже
    0.26
    Activations Density 0.004%

    No Known Activations