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. 24511
    Prev
    Next
    INDEX
    Explanations

    say "or"

    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
    ༜
    -0.09
    تعيين
    -0.08
    ꦕ
    -0.08
     Johns
    -0.08
    uci
    -0.07
    bezpieczeństw
    -0.07
    ﳎ
    -0.07
     Stuart
    -0.07
    罽
    -0.07
     formatting
    -0.07
    POSITIVE LOGITS
    いくら
    0.08
    .control
    0.07
    	input
    0.07
    union
    0.06
    古镇
    0.06
    生产和
    0.06
    punkt
    0.06
    MLElement
    0.06
    -&
    0.06
     MISS
    0.06
    Activations Density 0.022%

    No Known Activations