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. 71378
    Prev
    Next
    INDEX
    Explanations

    which

    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
     그냥
    -0.08
    制剂
    -0.08
     Shortly
    -0.08
    三年级
    -0.08
    ileges
    -0.07
    Doctors
    -0.07
     shaft
    -0.07
    psy
    -0.07
     cultivation
    -0.07
    .Constants
    -0.07
    POSITIVE LOGITS
    	end
    0.07
     Have
    0.06
    าม
    0.06
    �
    0.06
    -conf
    0.06
    꺅
    0.06
     deux
    0.06
    �
    0.06
     Go
    0.06
     Aless
    0.06
    Activations Density 0.042%

    No Known Activations