© 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. 151101
    Prev
    Next
    INDEX
    Explanations

    say commas

    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
    hamster
    -0.30
    WINDOW
    -0.27
    ramer
    -0.26
    autiful
    -0.26
    andelier
    -0.25
    èŁ¾
    -0.25
    ainers
    -0.25
    abee
    -0.24
    woke
    -0.24
    ä»»æĦı
    -0.24
    POSITIVE LOGITS
    ↵
    0.28
    ,
    0.27
    ç»Ī
    0.27
     Generated
    0.26
    ot
    0.26
    ns
    0.25
     Student
    0.25
     ns
    0.25
     GCC
    0.25
    ortion
    0.25
    Activations Density 0.114%

    No Known Activations