© 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. 111834
    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
    иÑĤеÑĤ
    -0.29
     seria
    -0.29
    è±¹
    -0.28
    è¦ģåģļåĪ°
    -0.26
    å¢ĥçķĮ
    -0.25
     nors
    -0.25
    å¢ĥ
    -0.25
    éļ¾åħ³
    -0.24
    pecia
    -0.24
    æł¼å±Ģ
    -0.24
    POSITIVE LOGITS
    uche
    0.27
    vey
    0.26
     nghiá»ĩp
    0.26
    çŃīéĥ¨éŨ
    0.25
    欺è¯Ī
    0.25
    ãĥ¡ãĥ¼ãĥ«
    0.25
    çĶ¢æ¥Ń
    0.24
    NEG
    0.24
    lement
    0.24
    ue
    0.24
    Activations Density 0.004%

    No Known Activations

    This feature has no known activations.