© 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. 43662
    Prev
    Next
    INDEX
    Explanations

    locations and names

    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
    yw
    -0.29
    sequ
    -0.26
    igua
    -0.26
     progressives
    -0.26
    abouts
    -0.25
    shi
    -0.25
    ä¸ĢçĶŁ
    -0.25
    é³į
    -0.25
    ypo
    -0.25
     sho
    -0.24
    POSITIVE LOGITS
     chÃŃ
    0.26
    utter
    0.26
    åī§ç»Ħ
    0.26
    åĩĨ
    0.25
    趴
    0.24
     ÑĢаÑģ
    0.24
    æĶ¸
    0.24
    еÑĢж
    0.23
    uto
    0.23
    åĺ»
    0.23
    Activations Density 0.002%

    No Known Activations