INDEX

Explanations

ancel

np_max-act · gemini-2.0-flash

New Auto-Interp

Configuration

mwhanna/qwen3-4b-transcoders/layer_11.safetensors

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

163,840

Data Type

float32

Hook Name

blocks.11.mlp.hook_in

Architecture

transcoder

Context Size

8,192

Dataset

monology/pile-uncopyrighted

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

ubb

-0.28

äº§

-0.27

etur

-0.27

 leans

-0.27

çĶ»

-0.26

lux

-0.26

å¤¹

-0.25

 allen

-0.25

../../../

-0.25

 produÃ§Ã£o

-0.24

POSITIVE LOGITS

artment

0.28

 Billboard

0.27

RIX

0.27

apons

0.27

ØªØŃØ±ÙĬØ±

0.26

chest

0.25

istring

0.25

æıĲæ¬¾

0.25

à¹Ģà¸ķ

0.25

åĬŀå¥½

0.24

Activations Density 0.013%

ancel

No Comments

No Known Activations