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. 36542
    Prev
    Next
    INDEX
    Explanations

    say one or two letters

    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
     Abraham
    -0.08
    אולם
    -0.07
    相同
    -0.07
     순간
    -0.07
    위원
    -0.07
    困難
    -0.07
     Herman
    -0.06
     Dale
    -0.06
    	cal
    -0.06
    PerPixel
    -0.06
    POSITIVE LOGITS
    电厂
    0.08
     expans
    0.07
     wakes
    0.07
    oted
    0.07
     sexes
    0.07
     PLAYER
    0.07
     reinforcement
    0.06
     breasts
    0.06
    🥤
    0.06
     vibration
    0.06
    Activations Density 0.004%

    No Known Activations