INDEX

Explanations

camera lenses

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

furt

-0.28

 HttpServletResponse

-0.28

/operators

-0.27

å¹´ä¸ĬåįĬå¹´

-0.25

.wikipedia

-0.25

çĵł

-0.25

mel

-0.25

ych

-0.24

 Myers

-0.24

oric

-0.24

POSITIVE LOGITS

æķ£

0.28

Cah

0.27

hek

0.27

ÑģÑĤÐ°Ð²ÐºÐ°

0.27

egan

0.27

centage

0.25

_tick

0.24

gee

0.24

 ÅŁek

0.24

roid

0.24

Activations Density 0.015%

camera lenses

No Comments

No Known Activations