INDEX

Explanations

Numerical ranges and comparisons

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

oose

-0.33

èĤ©

-0.26

 kÃª

-0.26

igate

-0.26

anse

-0.25

 Faster

-0.25

ean

-0.25

qh

-0.25

æ¶Īè´¹èĢħçļĦ

-0.25

ate

-0.25

POSITIVE LOGITS

cling

0.28

 range

0.28

 dependency

0.27

dependency

0.26

silver

0.26

rze

0.25

 rang

0.25

lip

0.25

bes

0.25

 bang

0.25

Activations Density 0.261%

Numerical ranges and comparisons

No Comments

No Known Activations