© 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. 22-TRANSCODER-HP
    7. 87788
    Prev
    Next
    INDEX
    Explanations

    't

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_22.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.22.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    itis
    -0.29
     reflex
    -0.28
    isque
    -0.26
    客åİħ
    -0.26
    éĥ½ä¸įæĺ¯
    -0.25
    xis
    -0.25
     Buk
    -0.24
    ä¸įæĺ¯ä¸Ģ个
    -0.24
    ref
    -0.24
    éĻĦ
    -0.24
    POSITIVE LOGITS
    abus
    0.28
    DW
    0.27
    aron
    0.26
    RW
    0.26
     bele
    0.26
     Dum
    0.25
    äºĪ
    0.24
     pertinent
    0.24
     whichever
    0.24
    æĻı
    0.24
    Activations Density 0.001%

    No Known Activations