© 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. 87666
    Prev
    Next
    INDEX
    Explanations

    much

    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
    ilon
    -0.27
    bulan
    -0.26
    hardt
    -0.25
    venes
    -0.25
    praak
    -0.25
     nämlich
    -0.25
    eon
    -0.24
    kle
    -0.24
    Viol
    -0.24
    icode
    -0.24
    POSITIVE LOGITS
    åį°è±¡æ·±åĪ»
    0.28
    ä»į
    0.27
     still
    0.27
    incipal
    0.26
    PEC
    0.26
    峡
    0.25
     equilibrium
    0.25
    好è¯Ħ
    0.24
    ä»įåľ¨
    0.24
     unanswered
    0.24
    Activations Density 0.045%

    No Known Activations