© 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. 150670
    Prev
    Next
    INDEX
    Explanations

    chest

    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
    ä¹ĭæĥħ
    -0.29
    urat
    -0.28
    ä¸įæ¸ħ
    -0.27
    auge
    -0.24
     //~
    -0.24
    .Dao
    -0.24
    reative
    -0.24
    è¿
    -0.23
    inject
    -0.23
     Dunn
    -0.23
    POSITIVE LOGITS
    esh
    0.28
    à¤ŀ
    0.26
    tree
    0.26
    æĤ£çĹħ
    0.26
    zheimer
    0.24
     barred
    0.24
    åĽ·
    0.24
     stripped
    0.24
    äºĮç»´çłģ
    0.23
    ç§Ģ
    0.23
    Activations Density 0.394%

    No Known Activations