© 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. 20-TRANSCODER-HP
    7. 142247
    Prev
    Next
    INDEX
    Explanations

    cerebral

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_20.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.20.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ãĥĻãĤ¹ãĥĪ
    -0.29
    ç¦ıå¾·
    -0.27
     Stephens
    -0.25
    æŁŀ
    -0.25
    æľĢ好çļĦ
    -0.24
    åī©
    -0.24
    æľĢå°ij
    -0.24
     swell
    -0.24
    EXAMPLE
    -0.23
    æľĢç¾İçļĦ
    -0.23
    POSITIVE LOGITS
     termin
    0.28
    agra
    0.28
    ispers
    0.28
    isper
    0.27
    å®Ĺ
    0.26
    é£İè²Į
    0.25
    ne
    0.24
    AMI
    0.24
     drops
    0.24
    Ne
    0.24
    Activations Density 17.170%

    No Known Activations