© 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. 58320
    Prev
    Next
    INDEX
    Explanations

    obstetrics and surgery

    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
    Not in Any Lists

    No Comments

    Negative Logits
    licher
    -0.29
    ata
    -0.27
    æłı
    -0.27
    æŀ£
    -0.26
     обÑıзаÑĤелÑĮ
    -0.25
    ease
    -0.25
    ä¸į解
    -0.24
    หาย
    -0.24
    cord
    -0.24
    å²Ĺ
    -0.24
    POSITIVE LOGITS
     uncompressed
    0.27
    ])**
    0.26
     fractured
    0.26
    对åѦçĶŁ
    0.25
    硬åĮĸ
    0.25
    .har
    0.24
    ///<
    0.24
    被æįķ
    0.24
     trailers
    0.24
     plut
    0.24
    Activations Density 0.907%

    No Known Activations