© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 33-TRANSCODER-HP
    7. 54563
    Prev
    Next
    INDEX
    Explanations

    it

    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
    Negative Logits
    iska
    -0.26
    aro
    -0.26
     sous
    -0.25
    _under
    -0.24
     Alt
    -0.23
    ACA
    -0.23
     under
    -0.23
     bead
    -0.23
    's
    -0.23
    (Cell
    -0.23
    POSITIVE LOGITS
    å®ĥ
    0.58
     it
    0.52
    å®ĥæĺ¯
    0.51
    å®ĥåı¯ä»¥
    0.45
    	it
    0.40
    it
    0.39
    ä½Ĩå®ĥ
    0.38
     nó
    0.37
    -it
    0.35
    _it
    0.35
    Activations Density 0.021%

    No Known Activations