© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 24-TRANSCODER-HP
    7. 150047
    Prev
    Next
    INDEX
    Explanations

    Code and foreign languages

    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
    minated
    -0.28
    åŁ¤
    -0.26
    erville
    -0.26
    ason
    -0.25
    Iteration
    -0.25
    lake
    -0.24
    æľĪä¸ĭ
    -0.24
    ,module
    -0.24
    河边
    -0.24
    @include
    -0.23
    POSITIVE LOGITS
    æŃ£
    0.31
    åįĬ个
    0.26
    ëł¹
    0.25
    ampo
    0.25
    ç»ĥ
    0.25
    обÑĢаз
    0.24
     MLA
    0.24
    agi
    0.23
     -:
    0.23
    (cid
    0.23
    Activations Density 0.085%

    No Known Activations