© 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. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    5. Qwen2.5-7B-IT
    7. Resid Post - 131k
    9. 15-RESID-POST-AA
    11. 119033
    Prev
    Next
    INDEX
    Explanations

    Patent

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-qwen2.5-7b-instruct/resid_post_layer_15/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     range
    -0.07
     sentient
    -0.07
    .render
    -0.07
    .xy
    -0.07
    兔
    -0.07
     autorelease
    -0.07
    .we
    -0.07
    .Form
    -0.07
     واحد
    -0.07
    免税
    -0.07
    POSITIVE LOGITS
    掏出
    0.07
     estates
    0.07
    ᨄ
    0.07
    instrument
    0.07
    说我
    0.07
    elines
    0.07
    患有
    0.07
    的好
    0.07
    塥
    0.07
    뇰
    0.07
    Activations Density 0.001%

    No Known Activations