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. 24273
    Prev
    Next
    INDEX
    Explanations

    Economic data reports

    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
    瀏覽
    -0.07
    并在
    -0.07
    റ
    -0.07
    .setCharacter
    -0.07
    峭
    -0.06
     الخامس
    -0.06
     fashionable
    -0.06
     ?>"><?
    -0.06
     ','
    -0.06
    idders
    -0.06
    POSITIVE LOGITS
    ⟱
    0.08
    ⧪
    0.07
    swith
    0.07
    wine
    0.07
     Prevention
    0.07
    engu
    0.07
    bw
    0.07
    ่วย
    0.07
    ığı
    0.07
    ragon
    0.07
    Activations Density 0.045%

    No Known Activations