© 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. 33-TRANSCODER-HP
    7. 53599
    Prev
    Next
    INDEX
    Explanations

    part

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_33.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.33.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     part
    -0.57
    çļĦä¸Ģéĥ¨åĪĨ
    -0.46
    part
    -0.42
     ÑĩаÑģÑĤÑĮ
    -0.40
    éĥ¨åĪĨ
    -0.39
    çļĦéĥ¨åĪĨ
    -0.39
    éĥ¨ä»½
    -0.37
     Part
    -0.37
    _part
    -0.36
    Part
    -0.34
    POSITIVE LOGITS
     o
    0.36
     a
    0.36
    	o
    0.32
     an
    0.30
    .o
    0.27
     our
    0.27
    ,o
    0.27
    a
    0.26
    ö
    0.26
    段
    0.26
    Activations Density 0.020%

    No Known Activations