© 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. 108778
    Prev
    Next
    INDEX
    Explanations

    foreign words

    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
    otal
    -0.26
    éĶĻ
    -0.26
    lyn
    -0.26
    家ãģ®
    -0.25
    æķ´é½IJ
    -0.25
     quarters
    -0.25
    QObject
    -0.25
    htable
    -0.25
    HOLDER
    -0.24
    ceb
    -0.24
    POSITIVE LOGITS
    类似
    0.26
    tas
    0.25
    éģ£
    0.24
     Shades
    0.24
     tas
    0.24
     cust
    0.24
    åħļç»Ħ
    0.24
    è¿Ľåĩº
    0.24
    ftware
    0.23
    systems
    0.23
    Activations Density 0.944%

    No Known Activations