© 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. 149521
    Prev
    Next
    INDEX
    Explanations

    Dates and death

    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
     suits
    -0.28
    rabbit
    -0.28
    è°¿
    -0.27
    rone
    -0.26
     banking
    -0.26
    вали
    -0.25
    ango
    -0.25
    ivant
    -0.25
     Simply
    -0.24
    rowser
    -0.24
    POSITIVE LOGITS
    omnia
    0.28
    第ä¸ĥ
    0.27
    æľĪä¸ĭæŬ
    0.27
    çģµæĦŁ
    0.25
    igmat
    0.25
    ilt
    0.25
    éĻħ
    0.25
    emplo
    0.24
    æł¸å®ļ
    0.24
    åij¨å²ģ
    0.24
    Activations Density 0.111%

    No Known Activations