© 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. 107751
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    å®ŀéĻħæĥħåĨµ
    -0.27
    ltr
    -0.27
     s
    -0.26
     baj
    -0.26
    egal
    -0.23
    åıijå±ķ缮æłĩ
    -0.23
    æĴĩ
    -0.23
    éĶĻ
    -0.23
    ä¿ĿçķĻ
    -0.23
    延ç»Ń
    -0.23
    POSITIVE LOGITS
    lsx
    0.26
    æĤ¦
    0.26
    è£Ķ
    0.25
    ists
    0.25
    .touch
    0.24
    uria
    0.24
    ophon
    0.24
    Cond
    0.24
    oph
    0.23
    conda
    0.23
    Activations Density 0.004%

    No Known Activations

    This feature has no known activations.