© 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. 107864
    Prev
    Next
    INDEX
    Explanations

    Research texts

    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
    standing
    -0.28
    举起
    -0.27
    enet
    -0.26
     puss
    -0.26
    awi
    -0.26
    crow
    -0.26
    cter
    -0.26
    chè
    -0.25
     exactly
    -0.25
    wg
    -0.25
    POSITIVE LOGITS
    éĺĹ
    0.27
    ause
    0.27
    ächst
    0.27
    createTime
    0.26
    ä¿ĿéĻ©åħ¬åı¸
    0.25
    ahkan
    0.25
    Ace
    0.24
    äºĭæķħåıijçĶŁ
    0.24
    éĢłæĪIJçļĦ
    0.24
    çļĦå¿ĥ
    0.24
    Activations Density 0.896%

    No Known Activations