© 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. 25-TRANSCODER-HP
    7. 106958
    Prev
    Next
    INDEX
    Explanations

    Balancing two concepts

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_25.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.25.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    .refs
    -0.32
    åŁºç¡Ģä¸Ĭ
    -0.29
    è°İ
    -0.26
    MET
    -0.26
     Ferd
    -0.26
    佯
    -0.26
     Mix
    -0.25
    ç»ıåķĨ
    -0.24
    使åħ¶
    -0.24
    False
    -0.24
    POSITIVE LOGITS
     accountability
    0.30
    ogo
    0.28
    é£İéĻ©ç®¡çIJĨ
    0.28
    éĢı
    0.28
     disease
    0.27
    æĥķ
    0.27
    çĸ¾çĹħ
    0.26
     uniqueness
    0.26
     UIL
    0.26
    iscal
    0.25
    Activations Density 0.894%

    No Known Activations