© 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
    2. Qwen3-4B
    3. 35-TRANSCODER-HP
    4. 39349
    Prev
    Next
    INDEX
    Explanations

    dashes

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_35.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.35.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    æĮīçħ§
    -0.35
    ä½Ĩæĺ¯
    -0.30
    æĪĸèĢħ
    -0.29
    为
    -0.28
    sel
    -0.28
    æĪĸèĢħåħ¶ä»ĸ
    -0.28
    以
    -0.27
    ipv
    -0.27
    us
    -0.27
    æľī
    -0.27
    POSITIVE LOGITS
    –↵↵
    0.33
     —↵↵
    0.32
    ↵				↵
    0.31
    &W
    0.31
    â̦↵↵
    0.31
    &T
    0.31
    &t
    0.30
     –↵↵
    0.30
    -↵↵
    0.30
    â̦.↵↵
    0.30
    Activations Density 0.046%

    No Known Activations