© 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. 107894
    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
    çĴł
    -0.28
    æŁĴ
    -0.25
    zza
    -0.25
    榻
    -0.25
    æĻ®äº¬
    -0.25
     Copa
    -0.25
    åįİ为
    -0.25
    oven
    -0.24
    lyph
    -0.24
    åħ¨åľº
    -0.24
    POSITIVE LOGITS
    ä½įäºİ
    0.51
     located
    0.41
    ä½įæĸ¼
    0.41
     Near
    0.41
     Located
    0.40
     near
    0.40
    near
    0.40
    åĮĹ京
    0.40
     London
    0.39
    æĿŃå·ŀ
    0.38
    Activations Density 1.959%

    No Known Activations