© 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. 43447
    Prev
    Next
    INDEX
    Explanations

    France

    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
    CEF
    -0.28
    yx
    -0.27
    zl
    -0.27
    aea
    -0.27
     Lamp
    -0.25
    umin
    -0.25
    ssf
    -0.25
    chia
    -0.25
    UCH
    -0.24
    uin
    -0.24
    POSITIVE LOGITS
    ä¸ĸçķĮ第ä¸Ģ
    0.28
    åĮºåĨħ
    0.27
    éĥ¾
    0.26
    well
    0.25
    -force
    0.25
    	define
    0.25
    oriously
    0.24
    placer
    0.24
    æĪĽ
    0.24
    æĸĩåĮĸåĴĮ
    0.24
    Activations Density 0.004%

    No Known Activations