© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    5. Qwen2.5-7B-IT
    7. Resid Post - 131k
    9. 15-RESID-POST-AA
    11. 111239
    Prev
    Next
    INDEX
    Explanations

    code

    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
    ┭
    -0.07
    ערב
    -0.07
    ccc
    -0.06
     trick
    -0.06
    뵈
    -0.06
    臑
    -0.06
     międzyn
    -0.06
     tops
    -0.06
    웜
    -0.06
     statistic
    -0.06
    POSITIVE LOGITS
    _attachments
    0.07
     Penguins
    0.07
     FUNCT
    0.07
     <%
    0.06
    valuate
    0.06
     willingness
    0.06
     Pickup
    0.06
    ikipedia
    0.06
     relação
    0.06
    自卑
    0.06
    Activations Density 0.603%

    No Known Activations