© 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. 23-TRANSCODER-HP
    7. 25340
    Prev
    Next
    INDEX
    Explanations

    legal trials

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_23.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.23.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     sign
    -0.30
     greet
    -0.27
     Glover
    -0.26
    Sign
    -0.26
     Signing
    -0.24
    æĬ¤
    -0.24
     signs
    -0.24
    éļľç¢į
    -0.24
    åı¯è¡ĮæĢ§
    -0.24
     va
    -0.24
    POSITIVE LOGITS
    审åĪ¤
    0.49
    审çIJĨ
    0.44
     acquitted
    0.42
    åĪ¤åĨ³
    0.41
     judicial
    0.40
    åĨ¤
    0.40
    åħ¬æŃ£
    0.40
    æ³ķåºŃ
    0.39
     verdict
    0.38
    åĪij
    0.38
    Activations Density 0.065%

    No Known Activations