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. 109307
    Prev
    Next
    INDEX
    Explanations

    Multiple languages

    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
    -http
    -0.08
    觑
    -0.08
     difer
    -0.07
    备战
    -0.07
     встр
    -0.07
     представ
    -0.07
    身边的
    -0.07
    床上
    -0.07
    برز
    -0.07
    >Login
    -0.07
    POSITIVE LOGITS
     kan
    0.07
     rhs
    0.07
     Sc
    0.07
    olithic
    0.06
     !(
    0.06
     Cyr
    0.06
     cds
    0.06
     np
    0.06
    ᵎ
    0.06
     Cond
    0.06
    Activations Density 0.017%

    No Known Activations