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. 131001
    Prev
    Next
    INDEX
    Explanations

    foreign language

    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
    傲
    -0.07
    mour
    -0.07
     accumulation
    -0.07
     beating
    -0.07
    routing
    -0.07
    .When
    -0.07
    modifiable
    -0.07
    .rf
    -0.07
     fertility
    -0.07
    "":
    -0.07
    POSITIVE LOGITS
    (hero
    0.07
     dúvida
    0.07
    picked
    0.07
     произведен
    0.07
    genres
    0.07
     onSelect
    0.06
    	selected
    0.06
    (np
    0.06
    HECK
    0.06
    _USERNAME
    0.06
    Activations Density 0.005%

    No Known Activations