© 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. 27-TRANSCODER-HP
    7. 56759
    Prev
    Next
    INDEX
    Explanations

    language

    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
    ycin
    -0.34
    undi
    -0.26
    FromClass
    -0.24
    ÑİÑīиÑħÑģÑı
    -0.24
     disproportion
    -0.24
     Lun
    -0.24
    neg
    -0.24
    addError
    -0.24
    ä¸ĢæĹı
    -0.24
    çIJĽ
    -0.24
    POSITIVE LOGITS
    è¯Ńè¨Ģ
    0.78
     language
    0.66
    çļĦè¯Ńè¨Ģ
    0.65
    èªŀè¨Ģ
    0.64
    language
    0.54
     words
    0.53
     Language
    0.52
    éĢļä¿Ĺ
    0.50
    åı£è¯Ń
    0.50
    _language
    0.50
    Activations Density 0.001%

    No Known Activations