INDEX

Explanations

the

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

ãģĦãģ¤

-0.27

io

-0.25

ioc

-0.24

æĹłæīĢ

-0.24

rig

-0.24

éĿ¢çĽ®

-0.24

ible

-0.24

irth

-0.24

 sÆ¡

-0.24

è¯ģä»¶

-0.23

POSITIVE LOGITS

ensed

0.28

å£°

0.27

(::

0.27

èĪįå¾Ĺ

0.26

"os

0.26

dorf

0.26

è¼ª

0.26

enos

0.25

ensen

0.25

(__('

0.25

Activations Density 0.003%

the

No Comments

No Known Activations