© 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. 151103
    Prev
    Next
    INDEX
    Explanations

    blockchain and cryptocurrency

    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
    Not in Any Lists

    No Comments

    Negative Logits
    lâ
    -0.28
    (KP
    -0.28
    æĸĩç§ij
    -0.27
     fant
    -0.26
    agus
    -0.26
     Macy
    -0.26
    çݩ家æĿ¥è¯´
    -0.25
     è¾ĵåĩº
    -0.25
    Validators
    -0.25
    åIJĿ
    -0.25
    POSITIVE LOGITS
    Principal
    0.30
     Principal
    0.28
     Thompson
    0.25
    ajo
    0.25
     principal
    0.25
    羣æŃ£çļĦ
    0.25
     Eu
    0.25
    ÑģÑĥд
    0.25
     sond
    0.25
    oulder
    0.24
    Activations Density 0.889%

    No Known Activations