Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Qwen2.5-7B-IT
    4. Resid Post - 131k
    5. 19-RESID-POST-AA
    6. 24640
    Prev
    Next
    INDEX
    Explanations

    psychological studies

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-qwen2.5-7b-instruct/resid_post_layer_19/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.19.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    At
    -0.07
     Shots
    -0.06
    ervo
    -0.06
    ömür
    -0.06
    مؤس
    -0.06
    	os
    -0.06
    cosa
    -0.06
     התביעה
    -0.06
    ᚙ
    -0.06
     GroupLayout
    -0.06
    POSITIVE LOGITS
     road
    0.07
    лок
    0.07
     penetrated
    0.07
     sufficiently
    0.06
    Reading
    0.06
    תיא
    0.06
    _Q
    0.06
     pracę
    0.06
    anked
    0.06
    ಠ
    0.06
    Activations Density 0.072%

    No Known Activations