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. 15-RESID-POST-AA
    6. 27576
    Prev
    Next
    INDEX
    Explanations

    issue

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-qwen2.5-7b-instruct/resid_post_layer_15/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    肚
    -0.09
    ("@
    -0.07
    他
    -0.07
     Garrett
    -0.07
     Wed
    -0.06
    ул
    -0.06
     born
    -0.06
    此人
    -0.06
     "@
    -0.06
    顯示
    -0.06
    POSITIVE LOGITS
    weep
    0.07
    _started
    0.07
    	tr
    0.07
    再去
    0.07
     SNMP
    0.07
    offset
    0.07
     prolong
    0.07
    vasive
    0.07
    Except
    0.07
    straße
    0.07
    Activations Density 0.008%

    No Known Activations