© 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. 108624
    Prev
    Next
    INDEX
    Explanations

    turbomachines

    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
    uate
    -0.29
    olute
    -0.28
    exter
    -0.26
    é¥ķ
    -0.26
    gence
    -0.26
    cape
    -0.26
    icrobial
    -0.26
    uars
    -0.25
    èijĹä½ľæ¬Ĭ
    -0.25
    holders
    -0.25
    POSITIVE LOGITS
    åħ¶æ¬¡æĺ¯
    0.29
    iox
    0.28
    деж
    0.26
    ä¹ĭå¤Ħ
    0.25
    thes
    0.25
    oz
    0.24
    ng
    0.24
     discarded
    0.23
     Follow
    0.23
    plex
    0.23
    Activations Density 0.210%

    No Known Activations