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. 27-RESID-POST-AA
    6. 130988
    Prev
    Next
    INDEX
    Explanations

    Titles, names, code

    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_27/trainer_1
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    vals
    -0.07
    ierung
    -0.07
    iblings
    -0.07
    フ
    -0.06
    (V
    -0.06
    ศาส
    -0.06
     killer
    -0.06
    themes
    -0.06
    亲属
    -0.06
    伉
    -0.06
    POSITIVE LOGITS
    	model
    0.07
    	type
    0.07
     nose
    0.07
     замеча
    0.07
     above
    0.06
    .scope
    0.06
    }});↵
    0.06
    itions
    0.06
     Modify
    0.06
    世界经济
    0.06
    Activations Density 0.068%

    No Known Activations