© 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. 107729
    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
    instead
    -0.32
     instead
    -0.32
    erset
    -0.29
     Counter
    -0.28
     Instead
    -0.28
    rather
    -0.26
     plutôt
    -0.26
    Instead
    -0.25
    trad
    -0.25
    esub
    -0.25
    POSITIVE LOGITS
    ä½ĵè´¨
    0.28
    æĩĤ
    0.27
    dale
    0.26
    Ware
    0.25
    opath
    0.25
    oping
    0.25
    ä¸Ģæł·
    0.24
    겨
    0.24
    å°Ĭ
    0.23
    ä¸į大
    0.23
    Activations Density 0.038%

    No Known Activations