© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 22-TRANSCODER-HP
    7. 111235
    Prev
    Next
    INDEX
    Explanations

    to

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_22.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.22.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    endif
    -0.26
    æĺ¯ä»Ģä¹Īåij¢
    -0.26
    })();
    -0.26
    åĪ°ä½į
    -0.26
    ä¸į代表
    -0.25
    iry
    -0.25
    å·¥ä½ľä½ľé£İ
    -0.24
    解çŃĶ
    -0.24
     indirectly
    -0.24
    SSION
    -0.24
    POSITIVE LOGITS
    asket
    0.28
    è¿Ľ
    0.27
     Pred
    0.27
    lays
    0.26
    ä¸įåĩº
    0.26
    кал
    0.26
    ÙĤات
    0.26
    :NO
    0.25
     Pin
    0.25
    (savedInstanceState
    0.24
    Activations Density 0.004%

    No Known Activations