© 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. 29799
    Prev
    Next
    INDEX
    Explanations

    percentages/statistics

    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
    战争
    -0.07
    Feedback
    -0.07
    เผย
    -0.07
    谌
    -0.07
     artists
    -0.07
     restore
    -0.07
    aken
    -0.06
    鏊
    -0.06
    裼
    -0.06
    _SN
    -0.06
    POSITIVE LOGITS
    _cats
    0.08
    โค
    0.07
    quite
    0.07
    (IB
    0.07
    集体经济
    0.07
     düzenleme
    0.07
     localtime
    0.07
     équipé
    0.07
    תרבות
    0.07
    管理体系
    0.07
    Activations Density 0.079%

    No Known Activations