© 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. 88307
    Prev
    Next
    INDEX
    Explanations

    Questions and gratitude

    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
    便åı¯
    -0.27
     prohibit
    -0.25
    çĭ¼
    -0.25
    çĤ¯
    -0.24
    ä¸ĭä¸ĢæŃ¥
    -0.24
    enen
    -0.24
     prost
    -0.23
    ä¸ĭä¸Ģ
    -0.23
    驯
    -0.23
    apter
    -0.23
    POSITIVE LOGITS
     intentions
    0.27
    intent
    0.26
    '))->
    0.25
    UIScreen
    0.25
     pomys
    0.24
     ado
    0.24
    .intent
    0.24
     iht
    0.23
    室åıĭ
    0.23
    fans
    0.23
    Activations Density 0.171%

    No Known Activations