© 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. 24-TRANSCODER-HP
    7. 149492
    Prev
    Next
    INDEX
    Explanations

    Legal or patent documents

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_24.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.24.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    cola
    -0.27
    éĹ¾
    -0.27
    éľ²
    -0.26
     dwell
    -0.25
    èį¡
    -0.25
    æĭ¥åłµ
    -0.24
    Monday
    -0.24
    har
    -0.24
    Probe
    -0.24
    Revision
    -0.24
    POSITIVE LOGITS
    AF
    0.26
    çģ
    0.25
    gfx
    0.24
    пÑĥÑĤ
    0.24
    æķ¢
    0.24
    kee
    0.24
     absolutely
    0.23
    xz
    0.23
    æĸ½
    0.23
    çĶ³è¯·äºº
    0.23
    Activations Density 0.010%

    No Known Activations