© 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. 7718
    Prev
    Next
    INDEX
    Explanations

    what to do

    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
    åĥ°
    -0.27
    çĶ¨äºİ
    -0.25
    ATORY
    -0.25
    @student
    -0.25
    вели
    -0.24
    uffy
    -0.24
    [to
    -0.24
    hal
    -0.24
    (slot
    -0.23
    çľĭå¾ħ
    -0.23
    POSITIVE LOGITS
     done
    0.32
    ìłķ
    0.29
    ô
    0.28
    ÑģÑĤавка
    0.27
    éĩĩåıĸ
    0.27
    åѤ
    0.27
    berapa
    0.26
    done
    0.26
    áºŃu
    0.26
    actions
    0.26
    Activations Density 0.015%

    No Known Activations