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. 131003
    Prev
    Next
    INDEX
    Explanations

    ).

    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
    ᆯ
    -0.08
     positivity
    -0.07
    	LP
    -0.07
     dirt
    -0.07
    Ti
    -0.07
    .Ma
    -0.07
     mutable
    -0.07
    一下子就
    -0.07
     Stay
    -0.07
     Mastery
    -0.07
    POSITIVE LOGITS
     oscillator
    0.07
    heed
    0.07
    symbol
    0.07
    因为我们
    0.07
     légère
    0.06
    Check
    0.06
    erve
    0.06
    دع
    0.06
    coln
    0.06
    lector
    0.06
    Activations Density 0.090%

    No Known Activations