INDEX

Explanations

in

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

[System

-0.30

quirer

-0.26

riers

-0.25

è¨Ĥ

-0.25

çĿĢçľ¼

-0.25

éļ¾çĤ¹

-0.24

ogen

-0.24

Dep

-0.24

ogens

-0.24

 Relay

-0.24

POSITIVE LOGITS

 usefulness

0.27

 commerce

0.27

struk

0.26

 disproportion

0.25

yw

0.25

unn

0.25

è®¡è¾ĥ

0.25

 toString

0.25

å°ıåº·

0.24

ä¹Łä¸įåı¯èĥ½

0.24

Activations Density 0.019%

in

No Comments

No Known Activations