© 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. 98079
    Prev
    Next
    INDEX
    Explanations

    probe

    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
     spd
    -0.28
     spons
    -0.26
     nerv
    -0.26
    ifest
    -0.26
    еÑģÑĮ
    -0.26
    Typed
    -0.24
    apor
    -0.24
    orial
    -0.24
    iple
    -0.23
    ergic
    -0.23
    POSITIVE LOGITS
    ç½ijåıĭè¯Ħ论
    0.28
     incident
    0.27
    itat
    0.27
    ä¿©
    0.24
    ót
    0.24
    åĢĴå¡Į
    0.24
    itto
    0.24
    ä¾¦å¯Ł
    0.23
    åĻ¨
    0.23
    cade
    0.23
    Activations Density 0.072%

    No Known Activations