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

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 31423
    Prev
    Next
    INDEX
    Explanations

    say Nebraska

    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
     השא
    -0.07
    rais
    -0.07
    سير
    -0.07
    auté
    -0.07
    Organization
    -0.06
    erà
    -0.06
    ría
    -0.06
    s
    -0.06
    egal
    -0.06
    מנכ
    -0.06
    POSITIVE LOGITS
    (Buffer
    0.07
    	BOOL
    0.07
    都已经
    0.07
    ℰ
    0.07
    此种
    0.07
     getInput
    0.07
    },{
    0.07
     관심
    0.07
    揕
    0.07
    新品
    0.07
    Activations Density 0.001%

    No Known Activations