© 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. 98857
    Prev
    Next
    INDEX
    Explanations

    [@

    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
    个çĻ¾åĪĨçĤ¹
    -0.28
    vascular
    -0.27
    ushing
    -0.26
     Forums
    -0.25
    toupper
    -0.24
    aho
    -0.24
    percentage
    -0.24
    =_("
    -0.23
     limited
    -0.23
     percentage
    -0.23
    POSITIVE LOGITS
    å¤Ħäºİ
    0.28
    å°±èĥ½
    0.27
    dj
    0.27
    ä¸Ģéĥ¨
    0.26
    éĥ¨éķ¿
    0.26
    ç³Ł
    0.25
    çłģ
    0.25
    ç¯ĩ
    0.25
    å°±è¦ģ
    0.25
    æľĭ
    0.25
    Activations Density 0.030%

    No Known Activations