© 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. 24-TRANSCODER-HP
    7. 151349
    Prev
    Next
    INDEX
    Explanations

    negative connotations

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_24.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.24.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    æ¸ħæ´ģ
    -0.27
    '</
    -0.26
    reno
    -0.26
    clean
    -0.26
    åıªèĥ½
    -0.25
     steady
    -0.25
    æĪijä¸įçŁ¥éģĵ
    -0.24
    岿
    -0.24
    æ¸ħçIJĨ
    -0.24
    æĶ¶æĭ¾
    -0.24
    POSITIVE LOGITS
    ä¸įåIJĪçIJĨ
    0.51
    ä¸įå½ĵ
    0.48
    èħIJè´¥
    0.45
    ä¸įèī¯
    0.45
     abusive
    0.44
     improperly
    0.43
     harmful
    0.43
     malformed
    0.42
     outdated
    0.40
     faulty
    0.40
    Activations Density 1.031%

    No Known Activations