© 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. 30-TRANSCODER-HP
    7. 96282
    Prev
    Next
    INDEX
    Explanations

    of

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_30.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.30.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     positioned
    -0.26
    .rawValue
    -0.26
    .pivot
    -0.24
    çĪ±åIJĥ
    -0.23
    .formData
    -0.23
     spread
    -0.23
     xtype
    -0.23
     gaining
    -0.23
    -runner
    -0.23
    iesen
    -0.23
    POSITIVE LOGITS
    å¦Ĥæŀľæĺ¯
    0.43
    å¦Ĥæŀľ
    0.41
    å¦Ĥæŀľæľī
    0.40
     if
    0.35
    å¦ĤæŀľæĤ¨
    0.34
    å¦Ĥæŀľä¸įæĺ¯
    0.34
    å¦Ĥæŀľä½ł
    0.34
     first
    0.33
    è¿ĻäºĽéĹ®é¢ĺ
    0.32
    	if
    0.31
    Activations Density 0.077%

    No Known Activations