© 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. 87987
    Prev
    Next
    INDEX
    Explanations

    Legal references

    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
    inan
    -0.28
    tfoot
    -0.28
    .Wrap
    -0.27
    åľ°ä¸Ń
    -0.26
    ospace
    -0.25
    _Runtime
    -0.25
    validated
    -0.25
    apat
    -0.25
    quoted
    -0.25
    è··
    -0.25
    POSITIVE LOGITS
     expensive
    0.28
    æľīä¸Ģå®ļçļĦ
    0.27
    re
    0.27
    å¤Ħ
    0.26
    âĢ¦↵↵↵
    0.26
    æľīåĪ©
    0.25
    owl
    0.24
    æľī两ç§į
    0.24
     Bul
    0.24
    he
    0.24
    Activations Density 0.018%

    No Known Activations