© 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. 129787
    Prev
    Next
    INDEX
    Explanations

    fun

    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
     fundament
    -0.28
    eyer
    -0.28
    æĭŁ
    -0.26
    ĸī
    -0.24
    åıįæĢĿ
    -0.23
    een
    -0.23
     fundamentals
    -0.23
     vow
    -0.23
    icos
    -0.23
     vess
    -0.22
    POSITIVE LOGITS
    niest
    0.32
    éĻħ
    0.28
    -loving
    0.26
    itude
    0.25
    asma
    0.25
    tol
    0.24
     Panda
    0.24
    zilla
    0.23
    entina
    0.23
    eren
    0.23
    Activations Density 0.177%

    No Known Activations