INDEX

Explanations

arteries

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

 underst

-0.31

iveau

-0.28

unden

-0.27

åĸĺ

-0.27

ivor

-0.26

Â¥

-0.25

Fred

-0.25

ÑĩÐ°ÑģÑĤ

-0.25

odef

-0.25

idi

-0.25

POSITIVE LOGITS

 TestUtils

0.26

 Pipes

0.25

 Lanc

0.25

Ĥ¬

0.25

usp

0.25

rowable

0.25

_enter

0.24

å¿«

0.24

ewood

0.24

 enterprise

0.23

Activations Density 0.006%

arteries

No Comments

No Known Activations