© 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. 33-TRANSCODER-HP
    7. 53935
    Prev
    Next
    INDEX
    Explanations

    words ending in "tion"

    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
    Not in Any Lists

    No Comments

    Negative Logits
    sky
    -0.30
    ky
    -0.28
    æ·ĸ
    -0.28
    trust
    -0.26
     Maxwell
    -0.26
    trad
    -0.26
    Prem
    -0.25
    Sky
    -0.25
    blink
    -0.25
    /GPL
    -0.25
    POSITIVE LOGITS
    ece
    0.32
    et
    0.31
    aton
    0.29
    etch
    0.28
    t
    0.28
    eb
    0.28
    edly
    0.27
    ek
    0.27
    eo
    0.27
    ely
    0.27
    Activations Density 0.015%

    No Known Activations