© 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. 98111
    Prev
    Next
    INDEX
    Explanations

    And

    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
    Appe
    -0.27
    æī«ä¸Ģæī«
    -0.25
    /screen
    -0.24
    éĩįçİ°
    -0.24
    /groups
    -0.24
     waivers
    -0.24
    ä¾¿å®ľ
    -0.24
    imet
    -0.24
    Everything
    -0.23
    åī¯æĢ»
    -0.23
    POSITIVE LOGITS
    ç°§
    0.28
    åĽºä½ĵ
    0.26
    -Day
    0.26
    äºı
    0.26
    orf
    0.26
    edList
    0.26
    æĵį
    0.26
    rance
    0.25
    -day
    0.25
    artisan
    0.23
    Activations Density 0.007%

    No Known Activations