© 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. 129291
    Prev
    Next
    INDEX
    Explanations

    programming questions and answers

    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
    Not in Any Lists

    No Comments

    Negative Logits
     shorthand
    -0.26
     Developer
    -0.25
     Detective
    -0.24
    tion
    -0.24
    Current
    -0.24
     infix
    -0.23
    éĺ²çĽĹ
    -0.23
    çĪĨçĤ¸
    -0.23
    _latest
    -0.23
    æ·ĭ
    -0.23
    POSITIVE LOGITS
    çĤ¹åĩ»æŁ¥çľĭ
    0.29
    afil
    0.28
    inery
    0.26
    вÑĥ
    0.25
    tru
    0.25
     scho
    0.25
     weighed
    0.25
     zug
    0.24
    ä¹°çļĦ
    0.23
    TURE
    0.23
    Activations Density 0.001%

    No Known Activations