INDEX

Explanations

Random text

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

 Trades

-0.28

çī¹æ®Ĭ

-0.27

 experiment

-0.25

 Experiment

-0.25

experiment

-0.25

umped

-0.25

 composer

-0.25

usk

-0.24

uffle

-0.24

otch

-0.24

POSITIVE LOGITS

çĶ·æľĭåıĭ

0.30

gÄ±

0.27

lesi

0.27

 Shan

0.26

imiter

0.26

itness

0.25

 translators

0.25

aksi

0.24

Matchers

0.24

 owners

0.24

Activations Density 0.023%

Random text

No Comments

No Known Activations