© 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. 41553
    Prev
    Next
    INDEX
    Explanations

    M

    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
    åĬĽè¿ĺæĺ¯
    -0.28
    бой
    -0.27
    ies
    -0.26
     sporting
    -0.26
    issy
    -0.25
    pragma
    -0.25
     imposs
    -0.25
    æĪĺ士æĿ¥è¯´
    -0.24
    charg
    -0.24
     Muss
    -0.23
    POSITIVE LOGITS
    ä½ı
    0.38
    icens
    0.33
    èµ·
    0.32
     residence
    0.28
    vin
    0.27
     Residence
    0.27
    ä½ıäºĨ
    0.27
    zo
    0.26
    Strip
    0.26
    èµ·äºĨ
    0.26
    Activations Density 0.002%

    No Known Activations