© 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. 18-TRANSCODER-HP
    7. 89044
    Prev
    Next
    INDEX
    Explanations

    and

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_18.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.18.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ä»İèĢĮ
    -0.27
    å¾Īåĸľæ¬¢
    -0.25
    ado
    -0.24
    ä¸Ģç¬ij
    -0.24
    ixo
    -0.23
    æĸ¹éĿ¢
    -0.23
    goog
    -0.23
     sentimental
    -0.23
    kontakte
    -0.23
    asa
    -0.23
    POSITIVE LOGITS
    âĢ³
    0.27
     overwhelmingly
    0.24
    åŁĶ
    0.24
    ruption
    0.24
    ()[
    0.23
     Tol
    0.23
    xit
    0.23
    ()['
    0.23
    è¯ģåĪ¸äº¤æĺĵ
    0.22
     tun
    0.22
    Activations Density 33.988%

    No Known Activations