© 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. 25-TRANSCODER-HP
    7. 109053
    Prev
    Next
    INDEX
    Explanations

    Warnings or negative constraints

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_25.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.25.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    åİļ
    -0.26
    ä¸įåı¯
    -0.26
    æ¤Ĵ
    -0.25
    æİ´
    -0.25
    èĴŁ
    -0.25
     Victim
    -0.24
    æīĭä¸Ĭ
    -0.24
    -paper
    -0.24
     victims
    -0.24
    _hor
    -0.24
    POSITIVE LOGITS
    antt
    0.30
     discounted
    0.29
    åĥ»
    0.29
     discount
    0.27
    ç§ĭ
    0.26
    midt
    0.26
    /downloads
    0.26
    sehen
    0.25
    otive
    0.25
     agree
    0.25
    Activations Density 0.907%

    No Known Activations