© 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. 27-TRANSCODER-HP
    7. 58627
    Prev
    Next
    INDEX
    Explanations

    couple

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_27.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.27.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
     ÑģобÑģÑĤвенно
    -0.28
    åĨħåľ°
    -0.26
    é«ĺåľ°
    -0.25
    æ¾į
    -0.25
    IID
    -0.25
    Ev
    -0.24
    æŧ
    -0.24
    ä¸įå¾Ĺå·²
    -0.24
    oods
    -0.24
     hon
    -0.23
    POSITIVE LOGITS
    agus
    0.26
    åıįå¼¹
    0.26
    è¿ĶåĽŀæIJľçĭIJ
    0.26
    æ³±
    0.25
    à¸ĵ
    0.25
    åı¯éĢļè¿ĩ
    0.24
    perms
    0.24
    edere
    0.23
     Switch
    0.23
    assador
    0.23
    Activations Density 0.073%

    No Known Activations