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. 44201
    Prev
    Next
    INDEX
    Explanations

    of

    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
    weather
    -0.07
     consenting
    -0.07
     light
    -0.07
     healthcare
    -0.07
    p
    -0.06
    .topic
    -0.06
     getP
    -0.06
    	http
    -0.06
     historical
    -0.06
    q
    -0.06
    POSITIVE LOGITS
    #----------------------------------------------------------------------------
    0.07
    (""),
    0.07
     nxt
    0.07
    正品
    0.07
    砄
    0.06
    (""))
    0.06
    一秒
    0.06
    YPD
    0.06
    蕺
    0.06
    調べ
    0.06
    Activations Density 0.058%

    No Known Activations