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. 36449
    Prev
    Next
    INDEX
    Explanations

    EXISTS

    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
    .panelControl
    -0.07
     CHILD
    -0.07
    树
    -0.07
    -json
    -0.07
    .ul
    -0.07
    directories
    -0.07
    mdp
    -0.06
     đây
    -0.06
    atk
    -0.06
    ҝ
    -0.06
    POSITIVE LOGITS
    _pemb
    0.07
                                            ↵
    0.07
     Session
    0.07
    ℭ
    0.07
    会展中心
    0.07
     SAC
    0.07
     Havana
    0.07
    ięć
    0.07
    Chris
    0.07
                                            
    0.07
    Activations Density 0.001%

    No Known Activations