INDEX

Explanations

auxiliary verbs

np_max-act · gemini-2.0-flash

New Auto-Interp

Configuration

mwhanna/qwen3-4b-transcoders/layer_23.safetensors

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

163,840

Data Type

float32

Hook Name

blocks.23.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

pac

-0.28

 Hazard

-0.25

éĶ¨

-0.25

 spared

-0.24

á½²

-0.24

`s

-0.24

 facility

-0.24

 ridden

-0.23

ä»¥åıĬ

-0.23

 dispens

-0.23

POSITIVE LOGITS

Ð¾ÐºÐ¾

0.26

meld

0.26

 RuntimeMethod

0.25

ilst

0.25

quette

0.24

[__

0.24

UILTIN

0.24

æŃ¤é¡¹

0.24

addock

0.23

 stoi

0.23

Activations Density 0.030%

auxiliary verbs

No Comments

No Known Activations