© 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. 58477
    Prev
    Next
    INDEX
    Explanations

    movement from one place

    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
     from
    -0.42
    _from
    -0.41
     From
    -0.40
    ä»İ
    -0.40
    -from
    -0.40
    From
    -0.39
    FromArray
    -0.38
    .from
    -0.36
    —from
    -0.35
    .From
    -0.35
    POSITIVE LOGITS
     into
    0.37
     vÃło
    0.35
    äºİ
    0.33
     Into
    0.33
     onto
    0.32
    _into
    0.32
     kepada
    0.32
    into
    0.31
    æĸ¼
    0.31
    åĪ°
    0.30
    Activations Density 0.005%

    No Known Activations