© 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. 30-TRANSCODER-HP
    7. 95541
    Prev
    Next
    INDEX
    Explanations

    T

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_30.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.30.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    еÑģп
    -0.26
    kos
    -0.25
     hosted
    -0.25
    nable
    -0.25
    host
    -0.25
    éĤ£å¤©
    -0.24
    unds
    -0.24
    åįĥéĩĮ
    -0.24
    aces
    -0.24
    pos
    -0.24
    POSITIVE LOGITS
    åIJĥäºı
    0.29
     meta
    0.28
    /meta
    0.26
    CompanyId
    0.26
     Professionals
    0.26
    æ³°å·ŀ
    0.26
     Tradition
    0.25
    ivid
    0.25
    éŀij
    0.24
    OutOfRangeException
    0.24
    Activations Density 0.002%

    No Known Activations