INDEX

Explanations

time sequencing

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

æīĩ

-0.28

ç£ķ

-0.28

åħļçļĦ

-0.27

à¦

-0.27

incess

-0.27

/errors

-0.26

nett

-0.25

 Mund

-0.25

èĹķ

-0.24

igs

-0.24

POSITIVE LOGITS

 evaluator

0.28

ä¸įä¸ĭ

0.27

æĶ¯

0.27

å®īå®ļ

0.26

 fuse

0.26

_clip

0.26

TestMethod

0.25

[((

0.25

Borders

0.25

(IT

0.25

Activations Density 0.010%

time sequencing

No Comments

No Known Activations