© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 22-TRANSCODER-HP
    7. 99277
    Prev
    Next
    INDEX
    Explanations

    I

    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
    Negative Logits
    ä¸Ģç§į
    -0.26
    .ResultSet
    -0.26
    âĤ¬“
    -0.25
    rica
    -0.25
    å°ıå§IJ
    -0.25
    æ²Į
    -0.24
    æ¿Ģ
    -0.24
    ä»Ģä¹Īåij¢
    -0.24
    ÐļÐIJ
    -0.24
    ivas
    -0.24
    POSITIVE LOGITS
    _flutter
    0.29
    imenti
    0.27
    liner
    0.26
    æijĨåľ¨
    0.26
    éľĨ
    0.26
    çĽ¸ä¿¡
    0.25
    Gl
    0.25
    uent
    0.25
    ä½İ温
    0.25
     gl
    0.25
    Activations Density 0.008%

    No Known Activations