© 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. 33-TRANSCODER-HP
    7. 52824
    Prev
    Next
    INDEX
    Explanations

    fall

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_33.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.33.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    j
    -0.30
     eff
    -0.29
    9
    -0.29
     hor
    -0.28
    è¸ı
    -0.28
     j
    -0.27
    SV
    -0.26
    å±±
    -0.26
    S
    -0.26
    sm
    -0.26
    POSITIVE LOGITS
    _UNUSED
    0.26
    iative
    0.26
    -demand
    0.26
    cline
    0.26
    itive
    0.26
    ipa
    0.26
    çıĤ
    0.26
    raries
    0.26
    /vendors
    0.25
    fdb
    0.25
    Activations Density 0.022%

    No Known Activations