INDEX

Explanations

substance

np_max-act · gemini-2.0-flash

New Auto-Interp

Configuration

mwhanna/qwen3-4b-transcoders/layer_2.safetensors

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

163,840

Data Type

float32

Hook Name

blocks.2.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

æľºåħ³

-0.26

åĬ¨

-0.25

Ã§

-0.25

 raised

-0.24

-0.23

↵↵

-0.23

un

-0.23

æĮģæľī

-0.23

åīĮ

-0.23

POSITIVE LOGITS

urat

0.27

idel

0.26

TURE

0.26

ophile

0.25

RAR

0.25

è¯¥æ¸¸æĪı

0.25

NONE

0.25

gard

0.25

å¹´äº§

0.25

hower

0.25

Activations Density 21.845%

substance

No Comments

No Known Activations