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. 6850
    Prev
    Next
    INDEX
    Explanations

    push notifications and FCM

    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
    㳘
    -0.08
     compromises
    -0.07
     odbył
    -0.07
     undergo
    -0.07
     القيام
    -0.07
     bruises
    -0.07
     đương
    -0.07
    𫷷
    -0.07
     waive
    -0.06
     מישה
    -0.06
    POSITIVE LOGITS
    три
    0.08
    _j
    0.07
    ​
    0.07
    美景
    0.07
    重要原因
    0.07
    ܔ
    0.07
    rop
    0.07
     ):↵
    0.07
    roe
    0.07
    〉
    0.07
    Activations Density 0.009%

    No Known Activations