© 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. 30-TRANSCODER-HP
    7. 96475
    Prev
    Next
    INDEX
    Explanations

    chemical or scientific analysis

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_30.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.30.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     draining
    -0.29
     forward
    -0.27
    æĸ¯å¡Ķ
    -0.27
    ä¸ĭæīĭ
    -0.27
    åIJİåĨį
    -0.25
    mando
    -0.24
    管çIJĨå±Ģ
    -0.24
    åIJijåīį
    -0.23
    icago
    -0.23
    ä¸į对
    -0.23
    POSITIVE LOGITS
    æ··
    0.30
    bish
    0.29
     Rif
    0.28
     trầm
    0.27
    çĶµçº¿
    0.26
     Fur
    0.26
     blues
    0.26
    çĶµè·¯
    0.26
    çŃĨ
    0.26
    å¯Ħ
    0.25
    Activations Density 0.007%

    No Known Activations