© 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. 12-TRANSCODER-HP
    7. 23377
    Prev
    Next
    INDEX
    Explanations

    scientific writing

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_12.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.12.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Pair
    -0.27
    cade
    -0.26
    Pair
    -0.25
    sthrough
    -0.25
    åĪį
    -0.24
    taire
    -0.23
    (LOG
    -0.23
     ÐĴладимиÑĢ
    -0.23
    HRESULT
    -0.23
    夫å¦ĩ
    -0.23
    POSITIVE LOGITS
    çĽĪ
    0.29
    ç·¨
    0.28
    å·¡åĽŀ
    0.28
     systemic
    0.26
    íĹĮ
    0.25
    ç¼ĸ
    0.25
    Merit
    0.24
     Dx
    0.24
     conc
    0.24
    管çIJĨç³»ç»Ł
    0.24
    Activations Density 0.008%

    No Known Activations