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. 35783
    Prev
    Next
    INDEX
    Explanations

    Development context

    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
    角色
    -0.09
    _kv
    -0.07
    電視
    -0.07
     fucked
    -0.07
    =Math
    -0.07
    แดด
    -0.07
     Paige
    -0.07
     problem
    -0.07
    $path
    -0.07
     Nikki
    -0.07
    POSITIVE LOGITS
     …↵↵
    0.06
    Detector
    0.06
     aqu
    0.06
     지
    0.06
     domin
    0.06
     교
    0.06
     INTERN
    0.06
    いただいた
    0.06
     ...\
    0.06
     ….
    0.06
    Activations Density 0.185%

    No Known Activations