INDEX

Explanations

errors and uncertainty

np_max-act · gemini-2.0-flash

New Auto-Interp

Configuration

mwhanna/qwen3-4b-transcoders/layer_7.safetensors

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

163,840

Data Type

float32

Hook Name

blocks.7.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

[color

-0.29

åĵī

-0.26

 concerted

-0.26

è¦ĨçĽĸ

-0.25

èµī

-0.25

_coverage

-0.24

 Sanford

-0.24

Coverage

-0.24

alo

-0.24

isper

-0.24

POSITIVE LOGITS

ppy

0.28

åĪ¤

0.27

çİ°å®ŀ

0.26

èĪªè¡Į

0.26

 reality

0.25

åģļæ³ķ

0.24

å¤ĩçĶ¨

0.24

à¸Īà¸³à¸ģ

0.24

-strip

0.24

.Short

0.24

Activations Density 0.000%

errors and uncertainty

No Comments

No Known Activations