© 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. 88333
    Prev
    Next
    INDEX
    Explanations

    Code or research publications

    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
    ous
    -0.30
    æĢı
    -0.29
    Own
    -0.25
    Mess
    -0.24
    ä¹ĭåīįçļĦ
    -0.24
    _rr
    -0.24
    (*
    -0.24
     +#+
    -0.24
    ?=.*
    -0.24
    OK
    -0.23
    POSITIVE LOGITS
    )test
    0.26
    notated
    0.23
    Subsystem
    0.23
    datal
    0.23
    –and
    0.22
    _where
    0.22
    [U
    0.22
    裳
    0.22
    alytics
    0.22
    esan
    0.22
    Activations Density 0.003%

    No Known Activations