INDEX

Explanations

ai

np_max-act · gemini-2.0-flash

New Auto-Interp

Configuration

mwhanna/qwen3-4b-transcoders/layer_7.safetensors

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

163,840

Data Type

float32

Hook Name

blocks.7.mlp.hook_in

Architecture

transcoder

Context Size

8,192

Dataset

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

å·´å·´

-0.30

site

-0.28

anja

-0.27

ÑīÐ¸Ð½

-0.27

azine

-0.26

 Ð¿ÐµÑĢÐµÐ²

-0.25

 intending

-0.25

 repeating

-0.25

æĺĿ

-0.25

-pattern

-0.25

POSITIVE LOGITS

éķ¿æ±Ł

0.28

 block

0.28

&action

0.27

ONO

0.27

èĤĿèĦı

0.27

Ã³ÅĤ

0.26

block

0.26

 makeStyles

0.26

 oceans

0.26

å°ģ

0.26

Activations Density 0.782%

ai

No Comments

No Known Activations