© 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. 107036
    Prev
    Next
    INDEX
    Explanations

    Court case documents

    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
    (coll
    -0.30
    (fragment
    -0.29
     collaps
    -0.27
     sworn
    -0.25
    ]\\
    -0.24
    åıĤä¸İ
    -0.24
    IALOG
    -0.24
    IRC
    -0.23
    [loc
    -0.23
    istics
    -0.23
    POSITIVE LOGITS
    ãģ¹ãģį
    0.27
     zab
    0.26
     Verm
    0.25
    setState
    0.25
    setItem
    0.24
    verity
    0.24
    æĶ¾æīĭ
    0.24
     którÄħ
    0.24
    éĶ¯
    0.24
    .did
    0.23
    Activations Density 1.044%

    No Known Activations