© 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. 40031
    Prev
    Next
    INDEX
    Explanations

    Words ending in "aria"

    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
    rts
    -0.29
    it
    -0.29
    createCommand
    -0.28
    btc
    -0.27
    rt
    -0.27
    et
    -0.26
    im
    -0.26
     vests
    -0.26
    om
    -0.26
     mouths
    -0.24
    POSITIVE LOGITS
    aria
    0.35
    aire
    0.34
    aring
    0.34
    arily
    0.32
    arer
    0.31
    arity
    0.31
    éĿ¢ç§¯
    0.29
    аÑĢи
    0.28
    ARING
    0.28
    area
    0.28
    Activations Density 0.001%

    No Known Activations