© 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. 24-TRANSCODER-HP
    7. 149225
    Prev
    Next
    INDEX
    Explanations

    web page snippets

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_24.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.24.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    ä¸įæĸŃåĪĽæĸ°
    -0.25
    çŁ¥å·±
    -0.24
    igy
    -0.24
    è¶ħ级
    -0.24
    顶å±Ĥ设计
    -0.24
    hall
    -0.24
    estro
    -0.23
    åħħåĪĨèĤ¯å®ļ
    -0.23
    ci
    -0.23
     specifics
    -0.23
    POSITIVE LOGITS
    æĬķèµĦé¡¹çĽ®
    0.30
    ÑģÑħ
    0.26
     Benson
    0.26
    isan
    0.25
    ptime
    0.25
    eld
    0.24
    uit
    0.24
    -taking
    0.24
     Reconstruction
    0.24
    æ¸ħåįķ
    0.24
    Activations Density 0.176%

    No Known Activations