Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    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. 115133
    Prev
    Next
    INDEX
    Explanations

    webpage revisions timestamps

    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
     seçen
    -0.08
     dispersed
    -0.07
    מבוגרים
    -0.07
     tę
    -0.06
    جسد
    -0.06
    Logged
    -0.06
    icing
    -0.06
     userID
    -0.06
     Directed
    -0.06
    钔
    -0.06
    POSITIVE LOGITS
    、、
    0.07
    oire
    0.07
     ?",
    0.07
     QUAL
    0.07
     dim
    0.06
    F
    0.06
    ф
    0.06
    	Dim
    0.06
    чист
    0.06
     Sinclair
    0.06
    Activations Density 0.004%

    No Known Activations