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. 36454
    Prev
    Next
    INDEX
    Explanations

    Scientific measurement standards

    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
    Translation
    -0.08
    	fwrite
    -0.07
     corpses
    -0.07
    .Cor
    -0.07
     Colomb
    -0.06
    �
    -0.06
    ◆
    -0.06
    חוש
    -0.06
    公安
    -0.06
     lle
    -0.06
    POSITIVE LOGITS
    بات
    0.07
    라면
    0.07
    inerary
    0.07
    inish
    0.07
     FX
    0.07
     epit
    0.07
     influences
    0.06
     arenas
    0.06
     goes
    0.06
     TimeZone
    0.06
    Activations Density 0.016%

    No Known Activations