INDEX

Explanations

The word "two"

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

Fs

-0.27

 Carlson

-0.26

apl

-0.25

åĩ«

-0.25

sw

-0.25

èĲ¥åħ»ä»·åĢ¼

-0.25

ä¸ĭæ²ī

-0.25

utan

-0.25

 Thousands

-0.25

å¤ľ

-0.24

POSITIVE LOGITS

asta

0.29

å¼¹

0.28

oe

0.28

å¸¸è¯Ĩ

0.26

 Leave

0.25

ingerprint

0.24

leave

0.24

å½ª

0.24

ost

0.23

hin

0.23

Activations Density 0.000%

The word "two"

No Comments

No Known Activations