INDEX

Explanations

code-like 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

(\<

-0.29

Ã¤nd

-0.26

ODY

-0.25

 degraded

-0.25

thesized

-0.24

 Ð¶ÑĥÑĢÐ½Ð°Ð»

-0.24

oure

-0.24

dep

-0.23

ç¡Ŀ

-0.23

 booked

-0.23

POSITIVE LOGITS

ç¨½

0.28

arine

0.26

ç²½åŃĲ

0.26

-hide

0.25

ewise

0.25

_Items

0.25

::::::::

0.25

 Dane

0.25

èĤ¡æ°ĳ

0.24

 operating

0.24

Activations Density 0.007%

code-like text

No Comments

No Known Activations