© 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. 112405
    Prev
    Next
    INDEX
    Explanations

    article excerpts

    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
    æĬ«
    -0.30
    请éĢīæĭ©
    -0.28
    æ¯ıæĹ¥
    -0.28
     expended
    -0.28
     dav
    -0.27
    修为
    -0.26
    (Is
    -0.26
    å²Ń
    -0.25
    ampled
    -0.24
    åħħåĢ¼
    -0.24
    POSITIVE LOGITS
    alth
    0.28
    _scheme
    0.27
    iko
    0.26
    ôn
    0.25
    èĩªçĦ¶èĢĮ
    0.25
    æĢĤ
    0.24
    åıįèĢĮ
    0.24
    lesi
    0.24
    åĪºæ¿Ģ
    0.24
    atisch
    0.24
    Activations Density 0.004%

    No Known Activations