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. 129696
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    isEqualTo
    -0.07
    看见
    -0.07
     cabbage
    -0.07
    yet
    -0.07
     auxiliary
    -0.07
    ице
    -0.07
    (Sub
    -0.07
     соглас
    -0.06
     stochastic
    -0.06
     assistance
    -0.06
    POSITIVE LOGITS
    当たり
    0.08
     getPath
    0.07
    귓
    0.07
     póź
    0.07
    おすす
    0.07
     sprzedaż
    0.07
     charm
    0.07
    	Client
    0.07
    硪
    0.07
    過ご
    0.06
    Activations Density 0.001%

    No Known Activations