© 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. 130219
    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
     stop
    -0.27
     common
    -0.26
     vehicles
    -0.26
     pk
    -0.26
     break
    -0.26
    eki
    -0.26
     session
    -0.25
    ittel
    -0.25
     dr
    -0.25
     vehicle
    -0.25
    POSITIVE LOGITS
    æłĹ
    0.29
    (mut
    0.27
    _SB
    0.26
    æĺ¾çĦ¶æĺ¯
    0.25
    åĨ³å®ļ
    0.25
    vard
    0.25
    loo
    0.24
    æĺ¾çĦ¶
    0.24
    Sig
    0.24
    ifiant
    0.24
    Activations Density 1.254%

    No Known Activations

    This feature has no known activations.