© 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. 14-TRANSCODER-HP
    7. 41158
    Prev
    Next
    INDEX
    Explanations

    Non-English language and code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_14.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.14.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    侵害
    -0.29
    Spoiler
    -0.28
    rowsers
    -0.27
     spoilers
    -0.26
    .rollback
    -0.26
    æĭ±
    -0.25
    aturday
    -0.25
    .pointer
    -0.25
     ratio
    -0.23
    åİ¢
    -0.23
    POSITIVE LOGITS
     EQUI
    0.26
    åIJ¸æĶ¶
    0.25
    ):-
    0.24
    奢ä¾Īåĵģ
    0.24
    -turned
    0.24
    rift
    0.24
     absorbed
    0.23
    åºĶä»ĺ
    0.23
    íķĺê²łëĭ¤
    0.23
    uren
    0.23
    Activations Density 0.052%

    No Known Activations