© 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. 53725
    Prev
    Next
    INDEX
    Explanations

    comparison

    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
     results
    -0.46
     Results
    -0.46
    results
    -0.42
    Results
    -0.40
     RESULTS
    -0.40
    _results
    -0.39
    	results
    -0.35
     exact
    -0.35
    (results
    -0.34
    RESULTS
    -0.33
    POSITIVE LOGITS
     â
    0.33
     vs
    0.30
     =
    0.29
    å²IJ
    0.29
     mism
    0.28
     versus
    0.27
     matches
    0.27
    Mir
    0.26
     MATCH
    0.26
    è¿ĺæľīä»Ģä¹Ī
    0.26
    Activations Density 0.007%

    No Known Activations