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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 88778
    Prev
    Next
    INDEX
    Explanations

    entity

    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
    橐
    -0.07
     insign
    -0.07
     Buen
    -0.07
     eminent
    -0.07
    鼯
    -0.07
     Klan
    -0.07
    ﻺ
    -0.07
    -free
    -0.07
     Lod
    -0.07
     الطفل
    -0.07
    POSITIVE LOGITS
    /database
    0.08
     STATS
    0.07
    _odd
    0.07
     $('#
    0.07
     Predicate
    0.07
     남
    0.07
    &action
    0.07
     Microsoft
    0.07
    andy
    0.07
    -opacity
    0.07
    Activations Density 0.002%

    No Known Activations