© 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. 12-TRANSCODER-HP
    7. 23667
    Prev
    Next
    INDEX
    Explanations

    culpability

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_12.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.12.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    å¼Ģå¥ĸ
    -0.27
    æĺŁç©º
    -0.25
    æѧè§Ĩ
    -0.25
     symb
    -0.25
    @[
    -0.24
    ત
    -0.24
    çİ°è¡Į
    -0.24
    subs
    -0.24
    -plane
    -0.23
    åħ¬äº¤
    -0.23
    POSITIVE LOGITS
    ece
    0.33
    stance
    0.27
    ä¸Ńä»ĭæľºæŀĦ
    0.25
    åѤ
    0.25
    ysi
    0.25
     оÑĢигинал
    0.25
    åºŁ
    0.25
     medial
    0.25
     impro
    0.24
    Ñıн
    0.24
    Activations Density 0.062%

    No Known Activations