© 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. 111448
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    éķij
    -0.24
     Gala
    -0.24
    %H
    -0.24
     Nec
    -0.24
    æĺ¯æĢİä¹Ī
    -0.23
    ÑĭваеÑĤÑģÑı
    -0.23
    éĽªèĬ±
    -0.23
    éĺ²çĽĹ
    -0.23
    è¿IJä½ľ
    -0.23
     Advantage
    -0.23
    POSITIVE LOGITS
    nerg
    0.28
    slot
    0.27
    Initializing
    0.27
    [attr
    0.26
    umbs
    0.26
     Tol
    0.25
     doubly
    0.25
     att
    0.25
    å·²æľī
    0.25
     witness
    0.24
    Activations Density 0.383%

    No Known Activations

    This feature has no known activations.