INDEX

Explanations

comma

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

å¥¹è¯´

-0.28

èĢĮä¸įæĺ¯

-0.26

chaft

-0.25

quia

-0.25

æĸ½

-0.25

çĶ¸

-0.25

she

-0.24

èĢĮéĿŀ

-0.24

ä¼ĺ

-0.24

systems

-0.24

POSITIVE LOGITS

flate

0.26

zept

0.25

intval

0.25

æµŀ

0.25

è²Ĥ

0.24

ainless

0.24

cmp

0.24

 teleport

0.24

compareTo

0.24

ç»Ģ

0.24

Activations Density 0.050%

comma

No Comments

No Known Activations