© 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. 18-TRANSCODER-HP
    7. 89903
    Prev
    Next
    INDEX
    Explanations

    formerly/as

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_18.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.18.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    éĴ©
    -0.28
    oque
    -0.27
    缸çĪ±
    -0.27
    ág
    -0.25
    usting
    -0.25
    oky
    -0.25
    RAIN
    -0.24
    åİŁæľīçļĦ
    -0.24
     borr
    -0.24
    究
    -0.24
    POSITIVE LOGITS
     Tale
    0.27
    ¡°
    0.27
    endif
    0.27
    innacle
    0.25
    éªĿ
    0.24
     cush
    0.23
     FuÃŁ
    0.23
    ç¶
    0.23
     Ä°nsan
    0.23
    éĻªä¼´
    0.23
    Activations Density 4.081%

    No Known Activations