© 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. 18-TRANSCODER-HP
    7. 88128
    Prev
    Next
    INDEX
    Explanations

    Programming / Russian

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_18.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.18.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    –↵↵
    -0.26
    adoras
    -0.25
    quil
    -0.25
    okus
    -0.25
    icide
    -0.25
    =pos
    -0.24
    vé
    -0.24
    icina
    -0.24
    æ¼Ķ
    -0.24
    没æľīä»»ä½ķ
    -0.24
    POSITIVE LOGITS
    éĵ¨
    0.27
    ise
    0.26
    ISE
    0.26
    æįħ
    0.26
    éĺģ
    0.26
    ä¸Ģç¯ĩ
    0.25
     composing
    0.25
    iena
    0.25
    ileo
    0.24
     SSE
    0.24
    Activations Density 1.591%

    No Known Activations