© 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. 106972
    Prev
    Next
    INDEX
    Explanations

    scientific texts

    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
    彪
    -0.29
     size
    -0.27
    è§Ħ模
    -0.27
    尺寸
    -0.27
    æī£
    -0.27
    ä¸įè´Ł
    -0.27
    ç»Īç»ĵ
    -0.27
    çĶ·
    -0.27
    Playable
    -0.26
    fos
    -0.26
    POSITIVE LOGITS
    å±
    0.32
    çİij
    0.31
     Computational
    0.27
    æĦĨ
    0.27
    eous
    0.27
     carta
    0.26
     Tear
    0.26
    çĶĺ
    0.25
    å¥ĩ纳
    0.25
     Traverse
    0.24
    Activations Density 1.101%

    No Known Activations