© 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. 41497
    Prev
    Next
    INDEX
    Explanations

    opha

    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
    wares
    -0.26
    é«»
    -0.26
    eways
    -0.25
    ä¸Ģä½ĵ
    -0.25
    idis
    -0.25
    ystack
    -0.25
    pora
    -0.25
    ILES
    -0.24
    iaux
    -0.24
     Lifetime
    -0.24
    POSITIVE LOGITS
    鹤
    0.30
    稳
    0.28
    ace
    0.28
     u
    0.28
    åıĹ欢è¿İ
    0.26
    丰满
    0.26
    ng
    0.25
    饱满
    0.25
    èı±
    0.25
     Ve
    0.25
    Activations Density 0.004%

    No Known Activations