© 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. 32-TRANSCODER-HP
    7. 43831
    Prev
    Next
    INDEX
    Explanations

    h

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_32.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.32.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Jad
    -0.30
    êt
    -0.29
    Å¡t
    -0.28
    .serialize
    -0.27
    ró
    -0.26
    дов
    -0.26
     Iter
    -0.25
    raid
    -0.25
     Raider
    -0.25
    sert
    -0.24
    POSITIVE LOGITS
     Ca
    0.33
    æ±Ĥ
    0.30
    è´Ŀ壳
    0.28
    åį¡
    0.28
    Ca
    0.27
    пиÑģан
    0.27
    社ä¼ļç»Ħç»ĩ
    0.26
    åĭī强
    0.26
    å¾®
    0.26
     voc
    0.25
    Activations Density 0.007%

    No Known Activations