© 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. 22-TRANSCODER-HP
    7. 113049
    Prev
    Next
    INDEX
    Explanations

    Liver

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_22.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.22.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    s
    -0.35
    squ
    -0.29
    sand
    -0.26
    ä»Ģä¹Īéĥ½
    -0.25
     dipl
    -0.24
    ipur
    -0.24
    sounds
    -0.23
    иÑĢование
    -0.23
    Lic
    -0.23
     Pike
    -0.23
    POSITIVE LOGITS
    注æĦıåĬĽ
    0.27
    ubes
    0.26
    ubic
    0.26
    opol
    0.26
    ä¸įåħį
    0.26
     öl
    0.24
    åĿļåĨ³
    0.24
    追éĹ®
    0.23
    çĹĩ
    0.23
    uble
    0.23
    Activations Density 0.051%

    No Known Activations