© 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. 32-TRANSCODER-HP
    7. 42626
    Prev
    Next
    INDEX
    Explanations

    code and documentation

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_32.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.32.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ä¸Ģåı£æ°Ķ
    -0.28
    _na
    -0.27
    avana
    -0.26
    é¨İ
    -0.26
     ham
    -0.25
     Norte
    -0.24
    inged
    -0.24
    ne
    -0.24
    (ord
    -0.24
    å¾ij
    -0.24
    POSITIVE LOGITS
    acci
    0.29
    æijĦ
    0.27
    æŶæŶ
    0.26
    åĢĴ
    0.25
    interface
    0.25
     iy
    0.24
     sist
    0.24
    æij
    0.24
    éĺ±
    0.24
    cess
    0.24
    Activations Density 0.000%

    No Known Activations