© 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. 25-TRANSCODER-HP
    7. 108916
    Prev
    Next
    INDEX
    Explanations

    Coding or software development

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_25.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.25.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    chemy
    -0.29
    ffen
    -0.26
    åı¯ä»¥
    -0.26
    æĶ¾å¼Ģ
    -0.25
    åı¯ä»¥æł¹æį®
    -0.24
    ling
    -0.24
    ãĥijãĥ¼ãĥĨãĤ£
    -0.24
     можно
    -0.24
    ventional
    -0.24
    绽
    -0.24
    POSITIVE LOGITS
     Jobs
    0.29
     imagin
    0.26
    çļĦæĥ³æ³ķ
    0.26
     ideas
    0.25
    _datas
    0.25
    çļĦæķĻåѦ
    0.24
     tq
    0.24
    å·¥ä¸ļ大åѦ
    0.24
     imag
    0.24
    .Mock
    0.24
    Activations Density 0.117%

    No Known Activations