INDEX

Explanations

articles

np_max-act · gemini-2.0-flash

New Auto-Interp

Configuration

mwhanna/qwen3-4b-transcoders/layer_23.safetensors

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

163,840

Data Type

float32

Hook Name

blocks.23.mlp.hook_in

Architecture

transcoder

Context Size

8,192

Dataset

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

iating

-0.28

 Census

-0.27

çī©

-0.25

æĮĤ

-0.25

 Code

-0.25

çĶŁäº§ç»ıèĲ¥

-0.24

unft

-0.24

åħīéĺ´

-0.23

çŃ¹å»º

-0.23

Ð°Ð¹ÑĤÐµ

-0.23

POSITIVE LOGITS

kp

0.26

||(

0.25

uben

0.25

æ²ģ

0.24

jom

0.24

blade

0.24

sl

0.24

imes

0.23

hou

0.23

å¼·ãģĦ

0.23

Activations Density 0.008%

articles

No Comments

No Known Activations