© 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. 42025
    Prev
    Next
    INDEX
    Explanations

    Assessing knowledge or abilities

    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
    åĿ¦åħĭ
    -0.28
    æĹ¥å¸¸çĶŁæ´»
    -0.27
    讲æķħäºĭ
    -0.27
    amed
    -0.25
    æľĢåıĹ欢è¿İ
    -0.25
    ented
    -0.24
    éİ®
    -0.24
    çĻĸ
    -0.24
    æ²³
    -0.24
    éĩİå¿ĥ
    -0.24
    POSITIVE LOGITS
     subject
    0.40
     retention
    0.35
     interest
    0.32
    æµģ
    0.31
     retaining
    0.30
     retain
    0.30
     topic
    0.30
    åĬ²
    0.29
     rem
    0.28
    ices
    0.28
    Activations Density 0.000%

    No Known Activations