INDEX

Explanations

Inter

np_max-act · gemini-2.0-flash

New Auto-Interp

Configuration

mwhanna/qwen3-4b-transcoders/layer_9.safetensors

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

163,840

Data Type

float32

Hook Name

blocks.9.mlp.hook_in

Architecture

transcoder

Context Size

8,192

Dataset

monology/pile-uncopyrighted

Embeds

IFrame

Link

Negative Logits

 pupil

-0.26

 stout

-0.25

Ham

-0.25

sez

-0.25

å¸ĪçĶŁ

-0.24

('''

-0.24

ä»¥åĲİ

-0.24

åķ¾

-0.24

cÃ³w

-0.23

å¹³æĹ¶

-0.22

POSITIVE LOGITS

åħ¥

0.27

é¢Ĩå¯¼

0.26

é©¼

0.25

dem

0.24

èľ¡

0.24

ongs

0.24

"+↵

0.23

 fares

0.23

 Ensure

0.23

çĥĽ

0.23

Activations Density 0.309%

Inter

No Known Activations