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. 2915
    Prev
    Next
    INDEX
    Explanations

    .from

    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
    盧
    -0.07
     sous
    -0.07
    魄
    -0.07
     går
    -0.07
    (propertyName
    -0.07
     Saul
    -0.07
     quasi
    -0.07
    ὀ
    -0.07
    بطل
    -0.07
    亚运会
    -0.07
    POSITIVE LOGITS
    AGE
    0.08
    ")))
    0.07
    Deal
    0.07
    /master
    0.06
    ")
    ↵
    ↵
    0.06
    	M
    0.06
     الج
    0.06
    Wake
    0.06
     inhibit
    0.06
    ']))
    0.06
    Activations Density 0.001%

    No Known Activations