© 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. 22-TRANSCODER-HP
    7. 129339
    Prev
    Next
    INDEX
    Explanations

    Jew

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_22.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.22.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    åıij
    -0.27
    æļĦ
    -0.26
    ução
    -0.24
    $"
    -0.24
    sx
    -0.23
    etal
    -0.23
    Numer
    -0.23
    åij½
    -0.23
    aos
    -0.23
    oins
    -0.23
    POSITIVE LOGITS
    çijĽ
    0.28
    encv
    0.28
     spin
    0.26
     Question
    0.26
    eslint
    0.26
    -pe
    0.25
    bers
    0.25
    spin
    0.24
     Spin
    0.24
    (pe
    0.24
    Activations Density 0.063%

    No Known Activations