INDEX

Explanations

Oil

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 Migration

-0.33

éĽ£

-0.31

Migration

-0.29

æľĢéļ¾

-0.27

rule

-0.27

éļ¾

-0.27

ÃŃg

-0.26

 migration

-0.26

Gre

-0.25

âİľ

-0.25

POSITIVE LOGITS

å®¤å¤ĸ

0.32

 required

0.27

 allowance

0.27

Lei

0.26

iller

0.26

åķ¬

0.26

å®¤åĨħ

0.25

Laf

0.25

-fetch

0.25

astr

0.25

Activations Density 0.002%

Oil

No Comments

No Known Activations