© 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. 23718
    Prev
    Next
    INDEX
    Explanations

    computation and data processing

    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
     parallel
    -0.32
    inger
    -0.30
    éħī
    -0.29
    å¹³è¡Į
    -0.27
     wash
    -0.27
    æĿIJæĸĻ
    -0.26
    -series
    -0.25
     material
    -0.25
     parallels
    -0.25
    parallel
    -0.25
    POSITIVE LOGITS
     pBuffer
    0.29
    (Buffer
    0.28
    æ·±åĬłå·¥
    0.27
    rema
    0.26
    çĸ¾çĹħçļĦ
    0.26
    æ½ŀ
    0.25
    دÙĬÙĦ
    0.25
    Derived
    0.25
     DER
    0.25
    æīŃ转
    0.24
    Activations Density 0.002%

    No Known Activations