© 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. 17880
    Prev
    Next
    INDEX
    Explanations

    emer

    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
     سن
    -0.08
    大型
    -0.08
     interpretations
    -0.07
    解开
    -0.07
     EventArgs
    -0.07
    	    ↵
    -0.06
    捆绑
    -0.06
    (canvas
    -0.06
    年由
    -0.06
    下的
    -0.06
    POSITIVE LOGITS
    .getBlock
    0.08
    社会保险
    0.07
     thường
    0.07
    -assets
    0.07
    _mirror
    0.07
    ייט
    0.07
    [edge
    0.07
    ﻼ
    0.07
    _attention
    0.07
    뎀
    0.07
    Activations Density 0.002%

    No Known Activations