© 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. 22-TRANSCODER-HP
    7. 98045
    Prev
    Next
    INDEX
    Explanations

    possessive pronouns

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_22.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.22.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    chunk
    -0.25
    å¹´çĶ±
    -0.25
    å°ıæŶåīį
    -0.24
    触
    -0.24
    hon
    -0.24
    æı©
    -0.23
    ç»ĨèĬĤ
    -0.23
    éĢĭ
    -0.23
    ıc
    -0.23
    ÑģÑĤÑĢо
    -0.23
    POSITIVE LOGITS
     Nin
    0.25
     wann
    0.25
     manners
    0.24
    antha
    0.24
    eenth
    0.24
     unfold
    0.24
    表éĿ¢ä¸Ĭ
    0.24
    éķ«
    0.24
    .flow
    0.24
    roker
    0.23
    Activations Density 0.012%

    No Known Activations