© 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. 35-TRANSCODER-HP
    7. 40335
    Prev
    Next
    INDEX
    Explanations

    words starting with colon

    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
    ",
    -0.40
    '',
    -0.36
     ",
    -0.36
    ',
    -0.36
     ',
    -0.35
    ”ï¼Į
    -0.35
     \\↵
    -0.33
     ##↵
    -0.33
     '''č↵
    -0.33
     """č↵
    -0.32
    POSITIVE LOGITS
    :/
    0.40
    :Boolean
    0.38
    :boolean
    0.37
    :Event
    0.36
    :green
    0.36
    :'+
    0.35
    :S
    0.35
    :D
    0.35
    :I
    0.34
    :Object
    0.34
    Activations Density 21.223%

    No Known Activations