© 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. 106976
    Prev
    Next
    INDEX
    Explanations

    code and lists

    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
    oyal
    -0.26
    éĵİ
    -0.26
    compact
    -0.26
    ople
    -0.25
    yre
    -0.24
     presidency
    -0.24
    elman
    -0.24
     rough
    -0.24
     McN
    -0.23
     abide
    -0.23
    POSITIVE LOGITS
    æĥħåĨµ
    0.29
    ç¿Ĵæħ£
    0.26
    hab
    0.25
    aits
    0.25
    èĤ¡
    0.25
    夹
    0.24
    ç»Ħ
    0.24
    resa
    0.24
     buffs
    0.24
    buf
    0.24
    Activations Density 0.146%

    No Known Activations