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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 6916
    Prev
    Next
    INDEX
    Explanations

    disclaimers

    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
    暗示
    -0.07
     finanzi
    -0.07
    osaic
    -0.06
     THREE
    -0.06
     pute
    -0.06
     dilig
    -0.06
     Opposition
    -0.06
    Ⲁ
    -0.06
     accusing
    -0.06
     CLOSE
    -0.06
    POSITIVE LOGITS
     phần
    0.08
    shared
    0.07
    	builder
    0.07
    高新区
    0.07
    eds
    0.07
    icide
    0.07
    샵
    0.07
    	CHECK
    0.07
     ammo
    0.07
     trademark
    0.07
    Activations Density 0.036%

    No Known Activations