© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 32-TRANSCODER-HP
    7. 43948
    Prev
    Next
    INDEX
    Explanations

    to or for

    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
     possible
    -0.28
    otron
    -0.28
    éĩĩ访æŶ
    -0.26
    è¿Ļåĩłä¸ª
    -0.26
     over
    -0.26
    è¿ĻçĤ¹
    -0.25
    è¿Ļäºĭ
    -0.25
    azing
    -0.25
    aur
    -0.24
    possible
    -0.24
    POSITIVE LOGITS
     jednak
    0.35
     wh
    0.35
     however
    0.34
    -wh
    0.31
    åѦçĶŁ
    0.31
    åĩłä¹İ
    0.29
    however
    0.29
    epend
    0.28
     students
    0.27
     However
    0.27
    Activations Density 0.001%

    No Known Activations