© 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. 98300
    Prev
    Next
    INDEX
    Explanations

    General topics

    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
    é«ĺæĢ§èĥ½
    -0.24
    .Packet
    -0.24
    TERN
    -0.24
     facil
    -0.24
    æĶ¾ç¼ĵ
    -0.24
    avern
    -0.23
     founded
    -0.23
    akt
    -0.23
     Prescription
    -0.23
    èĢĹè´¹
    -0.23
    POSITIVE LOGITS
    CAD
    0.26
    éķ¿çŁŃ
    0.25
     '::
    0.25
    èĥľ
    0.24
    etur
    0.24
    ibus
    0.24
    æĢ»çļĦ
    0.23
    ç»Łè®¡æķ°æį®
    0.23
    微信åı·
    0.23
    uously
    0.23
    Activations Density 0.109%

    No Known Activations