© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 27-TRANSCODER-HP
    7. 9799
    Prev
    Next
    INDEX
    Explanations

    something tucked or nestled

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_27.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.27.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    飫
    -0.29
     mounted
    -0.26
    lice
    -0.26
    èĴ´
    -0.25
    å±ĢéĻIJ
    -0.25
     Lace
    -0.24
    åĹŁ
    -0.24
    ×ĵ×ŀ×Ķ
    -0.23
     Alter
    -0.23
    åĩºçİ°
    -0.23
    POSITIVE LOGITS
    è¯Ń
    0.34
     down
    0.27
    .down
    0.27
    indx
    0.27
    MESS
    0.26
     speech
    0.26
    otlin
    0.25
    è·ĸ
    0.25
    ponsive
    0.25
    rement
    0.25
    Activations Density 0.002%

    No Known Activations