© 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. 149159
    Prev
    Next
    INDEX
    Explanations

    technical, academic texts

    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
    ange
    -0.26
    ÑĢоз
    -0.25
    å±ŀ
    -0.24
    屬
    -0.24
     Trit
    -0.24
    .beans
    -0.24
    Con
    -0.24
     internally
    -0.23
     disguised
    -0.23
    orea
    -0.22
    POSITIVE LOGITS
    两款
    0.26
    æĪij对
    0.25
    äºĨä¸Ģ份
    0.24
    åħ¼å®¹
    0.24
     coupons
    0.24
    hani
    0.23
    ampled
    0.23
     δ
    0.23
    kdir
    0.23
    δ
    0.23
    Activations Density 0.292%

    No Known Activations