© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 24-TRANSCODER-HP
    7. 150817
    Prev
    Next
    INDEX
    Explanations

    on

    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
    åıĭæĥħéĵ¾æİ¥
    -0.28
    æľ¬è½®
    -0.27
     perme
    -0.26
    æĭŁ
    -0.26
     Colbert
    -0.25
    亿åħĥ以ä¸Ĭ
    -0.24
    perms
    -0.23
    cline
    -0.23
    clist
    -0.23
     mirrors
    -0.23
    POSITIVE LOGITS
     dick
    0.32
    çĶŁåij½
    0.29
    WOOD
    0.27
    å¨ĥ
    0.26
     Advantage
    0.26
    inds
    0.25
    询éĹ®
    0.25
    POCH
    0.24
    SPEC
    0.24
    éĹ®è¯¢
    0.24
    Activations Density 0.928%

    No Known Activations