© 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. 23-TRANSCODER-HP
    7. 23404
    Prev
    Next
    INDEX
    Explanations

    0

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_23.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.23.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    èĦī
    -0.29
    壮
    -0.28
    å½±åĵįåĬĽ
    -0.28
    ifest
    -0.27
    æľ¬æ¬¡
    -0.27
    æĻ®åıĬ
    -0.25
    ellant
    -0.24
    è¡¥
    -0.23
     mustard
    -0.23
    olson
    -0.23
    POSITIVE LOGITS
    äºļæ´²
    0.28
    xffff
    0.28
    aye
    0.26
    驸
    0.26
    ä¸ĸçķĮä¸Ģæµģ
    0.25
    LIKELY
    0.25
    ish
    0.24
    averse
    0.24
    grep
    0.23
     Contracts
    0.23
    Activations Density 0.000%

    No Known Activations