© 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
    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. 5883
    Prev
    Next
    INDEX
    Explanations

    in

    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
    _FE
    -0.08
     consort
    -0.07
     virgin
    -0.07
     passionately
    -0.07
     xuân
    -0.07
    accumulator
    -0.07
    elps
    -0.07
    泔
    -0.07
     recommand
    -0.07
     stools
    -0.07
    POSITIVE LOGITS
    下调
    0.08
     head
    0.07
    ثال
    0.07
    .h
    0.07
    athering
    0.07
    ᛐ
    0.07
    	self
    0.07
    ds
    0.06
    ­tion
    0.06
    /s
    0.06
    Activations Density 0.006%

    No Known Activations