Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 71525
    Prev
    Next
    INDEX
    Explanations

    elaborating/answering questions

    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
     يكون
    -0.07
    Shapes
    -0.07
     seizing
    -0.07
    Opcode
    -0.06
    _spot
    -0.06
    akah
    -0.06
     OAuth
    -0.06
    عيش
    -0.06
     SAP
    -0.06
    ביקורת
    -0.06
    POSITIVE LOGITS
    rd
    0.08
    邓
    0.08
     prison
    0.07
     repell
    0.07
    布莱
    0.07
    mul
    0.07
     crucial
    0.07
    稿
    0.07
     yog
    0.07
                                                 
    0.07
    Activations Density 0.165%

    No Known Activations