© 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. 25-TRANSCODER-HP
    7. 109069
    Prev
    Next
    INDEX
    Explanations

    abstract concepts and processes

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_25.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.25.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    æµĭéĩı
    -0.30
    å°Ħ
    -0.27
    æ·±
    -0.26
    ä¸¥æł¼çļĦ
    -0.26
    跨度
    -0.26
    è¿ĺåĮħæĭ¬
    -0.26
    æ¸ħæ´Ĺ
    -0.26
    cka
    -0.26
    éĢıè§Ĩ
    -0.26
    éĹª
    -0.25
    POSITIVE LOGITS
    atur
    0.27
    izi
    0.25
    appropriate
    0.25
    goog
    0.25
     itemprop
    0.24
     approaches
    0.24
    wares
    0.24
     ~~
    0.24
    Scripts
    0.24
    crew
    0.23
    Activations Density 0.909%

    No Known Activations