© 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. 43312
    Prev
    Next
    INDEX
    Explanations

    Technical texts

    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
    sa
    -0.34
     san
    -0.32
    asa
    -0.31
    æĮļ
    -0.30
    san
    -0.28
    åľ»
    -0.27
    San
    -0.26
    离ä¸įå¼Ģ
    -0.25
    姨
    -0.25
    ook
    -0.25
    POSITIVE LOGITS
     Battle
    0.26
     esl
    0.25
     Hum
    0.25
    cope
    0.25
    foreign
    0.24
    Hum
    0.24
    Battle
    0.24
    èħĶ
    0.24
    ķĮ
    0.23
     lattice
    0.23
    Activations Density 0.000%

    No Known Activations