© 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. 23635
    Prev
    Next
    INDEX
    Explanations

    Scientific papers

    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
     baģlı
    -0.32
    å°½
    -0.29
    spect
    -0.27
    ams
    -0.26
    mani
    -0.26
     Bes
    -0.26
    æĢ§æĦŁ
    -0.25
    diet
    -0.25
     Faculty
    -0.25
    æĦ
    -0.23
    POSITIVE LOGITS
     apolog
    0.29
    baugh
    0.27
    ниÑĨ
    0.27
    EIF
    0.26
    ÑĢев
    0.25
    çĴĭ
    0.25
    isko
    0.25
    æľĪæľ«
    0.25
    [][
    0.25
    çĶ¨çĶµ
    0.24
    Activations Density 0.000%

    No Known Activations