© 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. 43577
    Prev
    Next
    INDEX
    Explanations

    Technical data/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
    责任ç¼ĸè¾ij
    -0.32
    rne
    -0.27
    ellow
    -0.26
    åĽĽäºĶ
    -0.25
    äºĶåħŃ
    -0.25
    hole
    -0.24
     Mechanical
    -0.24
    è°ŀ
    -0.24
    åħ¬å¹³
    -0.24
    _construct
    -0.24
    POSITIVE LOGITS
    åĵģçīĮçļĦ
    0.28
     brand
    0.28
    éĢ»
    0.26
    iker
    0.25
    mers
    0.25
    _cg
    0.25
    pot
    0.25
     po
    0.24
     immersion
    0.24
    cth
    0.24
    Activations Density 0.000%

    No Known Activations