© 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. 14-TRANSCODER-HP
    7. 41439
    Prev
    Next
    INDEX
    Explanations

    Formal writing and references

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_14.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.14.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     plots
    -0.31
    space
    -0.30
     plot
    -0.27
    umi
    -0.27
    alysis
    -0.26
    è¯ĬæīĢ
    -0.25
    çķı
    -0.25
     deals
    -0.25
    çĥŃ线
    -0.25
     classNames
    -0.24
    POSITIVE LOGITS
    epad
    0.26
    æĶ¶
    0.26
    çļĦåīįæıIJ
    0.26
    -validator
    0.25
    ymce
    0.25
    å§ĭ
    0.24
    åıĥ
    0.24
    ноп
    0.24
    kı
    0.24
    yun
    0.24
    Activations Density 0.094%

    No Known Activations