© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    5. Qwen2.5-7B-IT
    7. Resid Post - 131k
    9. 19-RESID-POST-AA
    11. 5794
    Prev
    Next
    INDEX
    Explanations

    technical discussions

    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
    之旅
    -0.07
     credentials
    -0.07
    UPS
    -0.07
     Müsl
    -0.07
    victim
    -0.07
    Output
    -0.07
    隃
    -0.06
     masa
    -0.06
     lunch
    -0.06
     {...
    -0.06
    POSITIVE LOGITS
    קבוצה
    0.07
    -y
    0.06
     programmers
    0.06
    ように
    0.06
    ивать
    0.06
     więcej
    0.06
    קצב
    0.06
     notorious
    0.06
    SIM
    0.06
    kraine
    0.06
    Activations Density 0.004%

    No Known Activations