© 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. 111418
    Prev
    Next
    INDEX
    Explanations

    Stop words

    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
    arius
    -0.26
     hum
    -0.26
    alker
    -0.26
    æĺ¯æľĢ
    -0.26
     undert
    -0.24
     should
    -0.24
     alc
    -0.24
    缮å½ķ
    -0.23
     are
    -0.23
    åħĪ
    -0.23
    POSITIVE LOGITS
     Beds
    0.28
     nämlich
    0.25
    æķĪæŀľ
    0.25
    çĤ¬
    0.24
    _locator
    0.24
    åľ¨ä»Ĭå¹´
    0.24
    qa
    0.23
    ction
    0.23
    otos
    0.23
    wu
    0.23
    Activations Density 0.003%

    No Known Activations