© 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. 99274
    Prev
    Next
    INDEX
    Explanations

    negative situations

    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
    bows
    -0.26
    gor
    -0.25
     Chop
    -0.24
    æŀģ
    -0.24
     alarm
    -0.24
    act
    -0.24
    arrow
    -0.24
     Orn
    -0.24
     alignment
    -0.24
    ÙħاÙĨ
    -0.24
    POSITIVE LOGITS
    没æľīä»Ģä¹Ī
    0.35
    就没æľī
    0.34
     NEVER
    0.34
    就没
    0.30
    eam
    0.29
     nowhere
    0.27
    ä¸įéĻIJ
    0.27
    éĥ½ä¸įæķ¢
    0.26
    æĶ¾è¿ĩ
    0.26
    ä¹Łæ²¡æľī
    0.26
    Activations Density 0.017%

    No Known Activations