INDEX

Explanations

flower

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

ighth

-0.29

REF

-0.28

conde

-0.27

ä¸ĢæĶ¯

-0.27

 boxed

-0.26

tu

-0.26

å²Į

-0.25

 wisely

-0.24

aur

-0.24

eref

-0.24

POSITIVE LOGITS

RAFT

0.28

è¡¾

0.25

 outdoor

0.25

ì°°

0.25

enia

0.25

idel

0.25

 Secret

0.25

rypt

0.25

Flo

0.24

é¥«

0.24

Activations Density 0.028%

flower

No Comments

No Known Activations