© 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. 43212
    Prev
    Next
    INDEX
    Explanations

    technical/scientific texts

    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
    çĥŁåĽ±
    -0.29
    èł²
    -0.26
    Hel
    -0.26
    thood
    -0.25
    gross
    -0.25
    å¡ijæĸĻ
    -0.25
     componentWillUnmount
    -0.24
    管éģĵ
    -0.24
    hed
    -0.24
    æݢ索
    -0.23
    POSITIVE LOGITS
     Trans
    0.36
     trans
    0.36
     imp
    0.34
    æħ¢
    0.33
    äºļ
    0.33
    trans
    0.32
    Trans
    0.32
    åĨ²åĩ»
    0.29
     TRANS
    0.29
    éĢı
    0.29
    Activations Density 0.010%

    No Known Activations